Updated on 2025/07/17

写真a

 
KOBAYASHI Takao
 
Organization
Museum and Archives Institute Professor
Title
Institute Professor
External link

Degree

  • Doctor of Engineering ( Tokyo Institute of Technology )

Research Interests

  • Signal Processing

  • Human Interface

  • ヒューマンインタフェース

  • 音声処理

  • 信号処理

  • Speech Processing

Research Areas

  • Informatics / Intelligent robotics

  • Informatics / Intelligent informatics

Education

  • Tokyo Institute of Technology   Graduate School, Division of Integrated Science and Engineering

    - 1982

      More details

  • Tokyo Institute of Technology   Interdisciplinary Graduate School of Science and Engineering

    - 1982

      More details

    Country: Japan

    researchmap

  • Tokyo Institute of Technology   School of Engineering

    - 1977

      More details

    Country: Japan

    researchmap

Research History

  • -:東京工業大学 大学院総合理工学研究科 教授

    1998

      More details

  • -:Tokyo Institute of Technology Interdisciplinary Graduate School of Scinence ant Engineering Professor

    1998

      More details

  • :東京工業大学 精密工学研究所 助教授

    1989 - 1998

      More details

  • :Tokyo Institute of Technology Precision and Intelligence Laboratory Associate Professor

    1989 - 1998

      More details

  • :Tokyo Institute of Technology Precision and Intelligence Laboratory Research Associate

    1982 - 1989

      More details

  • :東京工業大学 精密工学研究所 助手

    1982 - 1989

      More details

▼display all

Professional Memberships

  • 電子情報通信学会

      More details

  • The Institute of Electrical and Electronics Engineers

      More details

  • 日本音響学会

      More details

  • Information and Communication Engineers

      More details

  • The Institute of Electronics

      More details

  • The Institute of Electrical and Electronics Engineers

      More details

  • The Acoustical Society of Japan

      More details

  • Auditory and Visual Information Research Group

      More details

  • Information Processing Society of Japan

      More details

  • International Speech Communication Association

      More details

  • 情報処理学会

      More details

  • International Speech Communication Association

      More details

  • 視聴覚情報研究会

      More details

▼display all

Committee Memberships

  • 日本音響学会   評議員、編集委員会論文部会幹事 、評議員 、音声研究会委員長  

    2009 - 2010   

      More details

    Committee type:Academic society

    日本音響学会

    researchmap

  • 電子情報通信学会   音声研究専門委員会顧問、音声研究専門委員会委員長、音声研究専門委員会副委員長 、音声研究専門委員会幹事 、音声研究専門委員会委員 、音声研究専門委員会委員  

    2007 - 2008   

      More details

    Committee type:Academic society

    電子情報通信学会

    researchmap

  • 視聴覚情報研究会   監事、代表幹事  

    2006 - 2007   

      More details

    Committee type:Academic society

    視聴覚情報研究会

    researchmap

  • The Institute of Electrical and Electronics Engineers   Tokyo Section SAC Chair 、SPS Japan Chapter Secretary  

    2003 - 2004   

      More details

    Committee type:Academic society

    The Institute of Electrical and Electronics Engineers

    researchmap

  • The Institute of Electrical and Electronics Engineers   Tokyo Section SAC Chair 、SPS Japan Chapter Secretary  

    2003 - 2004   

      More details

    Committee type:Academic society

    The Institute of Electrical and Electronics Engineers

    researchmap

  • 情報処理学会   音声言語情報処理研究会委員  

    2002 - 2005   

      More details

    Committee type:Academic society

    情報処理学会

    researchmap

▼display all

Books

  • Speech Signal Processing Toolkit (SPTK)

    Consideration Books  2010  ( ISBN:9780935047721

     More details

  • Speech Signal Processing Toolkit (SPTK)

    Consideration Books  2010  ( ISBN:9780935047721

     More details

  • 韻律と音声言語情報処理

    丸善  2006  ( ISBN:4621076744

     More details

  • 人工知能学辞典

    共立出版  2005 

     More details

  • スペクトル解析ハンドブック(分担)

    朝倉書店  2004 

     More details

  • Galatea: Open-source software for developing anthropomorphic spoken dialog agents, in Life-Like Characters: Tools, Affective Functions, and Applications

    Springer  2004 

     More details

  • Galatea: Open-source software for developing anthropomorphic spoken dialog agents, in Life-Like Characters: Tools, Affective Functions, and Applications

    Springer  2004 

     More details

  • 新版音響用語辞典(分担)

    コロナ社  2003 

     More details

  • Introduction to Digital Integrated Circuits

    2000  ( ISBN:4785612029

     More details

  • ディジタル集積回路入門

    昭晃堂  2000  ( ISBN:4785612029

     More details

▼display all

MISC

  • HMM-Based Voice Conversion Using Quantized F0 Context

    Takashi Nose, Yuhei Ota, Takao Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E93D ( 9 )   2483 - 2490   2010.9

     More details

  • A Rapid Model Adaptation Technique for Emotional Speech Recognition with Style Estimation Based on Multiple-Regression HMM

    Yusuke Ijima, Takashi Nose, Makoto Tachibana, Takao Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E93D ( 1 )   107 - 115   2010.1

     More details

  • A Technique for Estimating Intensity of Emotional Expressions and Speaking Styles in Speech Based on Multiple-Regression HSMM

    Takashi Nose, Takao Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E93D ( 1 )   116 - 124   2010.1

     More details

  • A technique for estimating intensity of emotional expressions and speaking styles in speech based on multiple-regression HSMM

    Takashi Nose, Takao Kobayashi

    IEICE Trans. on Information and Systems   E93-D ( 1 )   116 - 124   2010

  • Tone correctness improvement in speaker-independent average-voice-based Thai speech synthesis

    Suphattharachal Chomphan, Takao Kobayashi

    SPEECH COMMUNICATION   51 ( 4 )   330 - 343   2009.4

     More details

  • HMM-Based Style Control for Expressive Speech Synthesis with Arbitrary Speaker's Voice Using Model Adaptation

    Takashi Nose, Makoto Tachibana, Takao Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E92D ( 3 )   489 - 497   2009.3

     More details

  • Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm

    Junichi Yamagishi, Takao Kobayashi, Yuji Nakano, Katsumi Ogata, Juri Isogai

    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING   17 ( 1 )   66 - 83   2009.1

     More details

  • Phone duration modeling using gradient tree boosting

    Junichi Yamagishi, Hisashi Kawai, Takao Kobayashi

    SPEECH COMMUNICATION   50 ( 5 )   405 - 415   2008.5

     More details

  • Tone correctness improvement in speaker dependent HMM-based Thai speech synthesis

    Suphattharachai Chomphan, Takao Kobayashi

    SPEECH COMMUNICATION   50 ( 5 )   392 - 404   2008.5

     More details

  • Incorporation of phrase intonation to context clustering for average voice models in HMM-based Thai speech synthesis

    Suphattharachai Chomphan, Takao Kobayashi

    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12   4637 - 4640   2008

     More details

  • Component-based face detection method for various types of occluded faces

    Kiyoto Ichikawa, Takeshi Mita, Osamu Hori, Takao Kobayashi

    Proc. 2008 3rd International Symposium on Communications, Control, and Signal Processing   538 - 543   2008

  • “Component-based Occluded Face Detection using AdaBoost and Decision Tree”

    Kiyoto Ichikawa, Takao Kobayashi, Takeshi Mita, Osamu Hori

    Journal of the Institute of Image Electronics Engineers of Japan   37 ( 4 )   419 - 427   2008

     More details

  • 顔パーツを利用した隠れを含む顔の検出方法

    市川清人, 三田雄志, 堀 修, 小林隆夫

    画像電子学会誌   37 ( 4 )   419 - 427   2008

  • Component-based face detection method for various types of occluded faces

    Kiyoto Ichikawa, Takeshi Mita, Osamu Hori, Takao Kobayashi

    Proc. 2008 3rd International Symposium on Communications, Control, and Signal Processing   538 - 543   2008

  • A style control technique for HMM-based expressive speech synthesis

    Takashi Nose, Junichi Yamagishi, Takashi Masuko, Takao Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E90D ( 9 )   1406 - 1413   2007.9

     More details

  • A hidden semi-Markov model-based speech synthesis system

    Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayasih, Tadashi Kitamura

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E90D ( 5 )   825 - 834   2007.5

     More details

  • State duration modeling for HMM-based speech synthesis

    Heiga Zen, Takashi Masuko, Keiichi Tokuda, Takayoshi Yoshimura, Takao Kobayasih, Tadashi Kitamura

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E90D ( 3 )   692 - 693   2007.3

     More details

  • Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training

    Junichi Yamagishi, Takao Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E90D ( 2 )   533 - 543   2007.2

     More details

  • Implementation and evaluation of an HMM-based Thai speech synthesis system

    Suphattharachai Chomphan, Takao Kobayashi

    Proc. 8th Annual Conference of the International Speech Communication Association   INTERSPEECH 2007   2849 - 2852   2007

     More details

  • Model adaptation approach to speech synthesis with diverse voices and styles

    Junichi Yamagishi, Takao Kobayashi, Makoto Tachibana, Katsumi Ogata, Yuji Nakano

    Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP 2007   1233 - 1236   2007

  • Implementation and evaluation of an HMM-based Thai speech synthesis system

    Suphattharachai Chomphan, Takao Kobayashi

    Proc. 8th Annual Conference of the International Speech Communication Association   INTERSPEECH 2007   2849 - 2852   2007

     More details

  • Model adaptation approach to speech synthesis with diverse voices and styles

    Junichi Yamagishi, Takao Kobayashi, Makoto Tachibana, Katsumi Ogata, Yuji Nakano

    Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP 2007   1233 - 1236   2007

  • Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training

    Junichi Yamagishi, Takao Kobayashi

    IEICE Trans. on Information and Systems   E90-D ( 2 )   533 - 543   2007

  • Performance evaluation of HMM-based style classification with a small amount of training data

    Makoto Tachibana, Keigo Kawashima, Junichi Yamagishi, Takao Kobayashi

    Proc. 8th Annual Conference of the International Speech Communication Association   INTERSPEECH 2007   2261 - 2264   2007

     More details

  • Performance evaluation of HMM-based style classification with a small amount of training data

    Makoto Tachibana, Keigo Kawashima, Junichi Yamagishi, Takao Kobayashi

    Proc. 8th Annual Conference of the International Speech Communication Association   INTERSPEECH 2007   2261 - 2264   2007

     More details

  • A style adaptation technique for speech synthesis using HSMM and suprasegmental features

    M Tachibana, J Yamagishi, T Masuko, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E89D ( 3 )   1092 - 1099   2006.3

     More details

  • Acoustic Model Training Based on Linear Transformation and MAP Modification for HSMM-Based Speech Synthesis

    Katsumi Ogata, Makoto Tachibana, Junichi Yamagishi, Takao Kobayashi

    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5   INTERSPEECH 2006 - ICSLP   1328 - 1331   2006

     More details

    Language:English  

    Web of Science

    researchmap

  • Constrained Structural Maximum A Posteriori Linear Regression for Average-Voice-Based Speech Synthesis

    Yuji Nakano, Makoto Tachibana, Junichi Yamagishi, Takao Kobayashi

    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5   INTERSPEECH 2006 - ICSLP   2286 - 2289   2006

     More details

    Language:English  

    Web of Science

    researchmap

  • HSMM-based model adaptation algorithms for average-voice-based speech synthesis

    Junichi Yamagishi, Katsumi Ogata, Yuji Nakano, Juri Isogai, Takao Kobayashi

    2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13   ICASSP 2006   77 - 80   2006

     More details

    Language:English  

    Web of Science

    researchmap

  • Human walking motion synthesis with desired pace and stride length based on HSMM

    N Niwase, J Yamagishi, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E88D ( 11 )   2492 - 2499   2005.11

     More details

  • Speech synthesis with various emotional expressions and speaking styles by style interpolation and morphing

    M Tachibana, J Yamagishi, T Masuko, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E88D ( 11 )   2484 - 2491   2005.11

     More details

  • Model adaptation and adaptive training using ESAT algorithm for HMM-based speech synthesis

    Juri Isogai, Junichi, Yamagishi, Takao Kobayashi

    Proc. 9th European Conference on Speech Communication and Technology   INTERSPEECH 2005   2597 - 2600   2005

     More details

  • A Wavelet based noise reduction algorithm for speech signal corrupted by coloured noise

    Vladimir Braquet, Takao Kobayashi

    Proc. 9th European Conference on Speech Communication and Technology   INTERSPEECH 2005   2073 - 2076   2005

     More details

  • Acoustic modeling of speaking styles and emotional expressions in HMM-based speech synthesis

    Junichi Yamagishi, Koji Onishi, Takashi Masuko, Takao Kobayashi

    IEICE Trans. Information and Systems   E88-D ( 3 )   502 - 509   2005

  • Adaptive training for hidden semi-Markov model

    Junichi Yamagishi, Takao Kobayashi

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   I   I365 - I368   2005

     More details

    Language:English   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.1109/ICASSP.2005.1415126

    Scopus

    researchmap

  • Acoustic modeling of speaking styles and emotional expressions in HMM-based speech synthesis

    Junichi Yamagishi, Koji Onishi, Takashi Masuko, Takao Kobayashi

    IEICE Trans. Information and Systems   E88-D ( 3 )   502 - 509   2005

  • Voiced/unvoiced determination of speech signal in noisy environment using harmonicity measure based on instantaneous frequency

    Dhany Arifianto, Takao Kobayashi

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   I   I877 - I880   2005

     More details

    Language:English   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.1109/ICASSP.2005.1415254

    Scopus

    researchmap

  • Adaptive training for hidden semi-Markov model

    Junichi Yamagishi, Takao Kobayashi

    Proc. 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP 2005   365 - 368   2005

  • Audio signal enhancement using multi-stage spectral subtraction

    Masatsugu Okazaki, Toshifumi Kunimoto, Takao Kobayashi

    IEICE Trans. on Information and Systems, Pt.2 (Japanese Ed.)   J88-D-II ( 12 )   2301 - 2310   2005

     More details

  • Performance evaluation of style adaptation for hidden semi-Markov model based speech synthesis

    Makoto Tachibana, Junich Yamagishi, Takashi Masuko, Takao Kobayashi

    Proc. 9th European Conference on Speech Communication and Technology   INTERSPEECH 2005   2805 - 2808   2005

     More details

  • 多段スペクトルサブトラクション法を用いた楽音の強調

    岡崎雅嗣, 国本利文, 小林隆夫

    電子情報通信学会論文誌   J88-D-II ( 12 )   2301 - 2310   2005

     More details

  • Performance evaluation of style adaptation for hidden semi-Markov model based speech synthesis

    Makoto Tachibana, Junich Yamagishi, Takashi Masuko, Takao Kobayashi

    Proc. 9th European Conference on Speech Communication and Technology   INTERSPEECH 2005   2805 - 2808   2005

     More details

  • Model adaptation and adaptive training using ESAT algorithm for HMM-based speech synthesis

    Juri Isogai, Junichi, Yamagishi, Takao Kobayashi

    Proc. 9th European Conference on Speech Communication and Technology   INTERSPEECH 2005   2597 - 2600   2005

     More details

  • A Wavelet based noise reduction algorithm for speech signal corrupted by coloured noise

    Vladimir Braquet, Takao Kobayashi

    Proc. 9th European Conference on Speech Communication and Technology   INTERSPEECH 2005   2073 - 2076   2005

     More details

  • Robust F-0 estimation of speech signal using harmonicity measure based on instantaneous frequency

    D Arifianto, T Tanaka, T Masuko, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E87D ( 12 )   2812 - 2820   2004.12

     More details

    Language:English  

    Web of Science

    researchmap

  • Galatea: An anthropomorphic spoken dialogue agent toolkit

    27 - 28   2004

     More details

  • Performance evaluation of style adaptation using context clustering decision tree

    Proc. the 2004 Spring Meeting of the Acoustical Society of Japan   I ( 1-7-22 )   255 - 256   2004

     More details

  • A study on style adaptation using structural MAPLR in HMM-based speech synthesis

    Proc. the 2004 Spring Meeting of the Acoustical Society of Japan   I ( 1-7-23 )   257 - 258   2004

     More details

  • Simultaneous modeling of location and duration of pause based on multi-space probability distribution

    Proc. the 2004 Spring Meeting of the Acoustical Society of Japan   I ( 2-P-21 )   371 - 372   2004

     More details

  • Generation of ball catching and throwing movements with arbitrarily prescribed ball position and speed

    Proc. the 65th National Convention of IPSJ   4 ( 3B-6 )   89 - 90   2004

     More details

  • An HMM-based approach to speaker-dependent 100 bit/s speech coding

    Takahiro Hoshiya, Heiga Zen, Shinji Sako Keiichi, Tokuda Takashi Masuko Takao Kobayashi, Tadashi Kitamura

    Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing, Conference CD-ROM   ( 1.5 )   6 pages   2004

     More details

  • 隠れセミマルコフモデルに基づく音声合成システムにおける最尤線形回帰によるスタイル適応の検討

    山岸順一, 橘誠, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   104 ( SP2004-49 )   13 - 18   2004

     More details

  • HMM音声合成における多様なスタイル実現のための制御法

    宮永圭介, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   104 ( SP2004-7 )   35 - 40   2004

     More details

  • 多空間確率分布に基づくポーズのモデル化

    尾関創, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   104 ( SP2004-8 )   41 - 46   2004

     More details

  • 隠れセミマルコフモデルに基づく音声合成におけるスタイル適応の評価

    橘誠 山岸順一, 益子貴史, 小林隆夫

    日本音響学会2004年秋季研究発表会講演論文集   I ( 3-2-9 )   333 - 334   2004

     More details

  • HMM音声合成のための継続長分布付き再推定

    全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2004年春季研究発表会講演論文集   I ( 1-7-6 )   223 - 224   2004

     More details

  • HMM音声合成における対数正規分布による状態継続長のモデル化の検討

    山岸順一, 益子貴史, 小林隆夫

    日本音響学会2004年春季研究発表会講演論文集   I ( 1-7-7 )   225 - 226   2004

     More details

  • コンテキストクラスタリング決定木を用いた発話スタイル適応の評価

    橘誠 山岸順一, 益子貴史, 小林隆夫

    日本音響学会2004年春季研究発表会講演論文集   I ( 1-7-22 )   255 - 256   2004

     More details

  • HMM音声合成における構造的MAPLRによる発話スタイルの多様化の検討

    参納大樹, 山岸順一, 益子貴史, 小林隆夫

    日本音響学会2004年春季研究発表会講演論文集   I ( 1-7-23 )   257 - 258   2004

     More details

  • 多空間確率分布によるポーズの位置と長さの同時モデル化

    尾関創, 益子貴史, 小林隆夫

    日本音響学会2004年春季研究発表会講演論文集   I ( 2-P-21 )   371 - 372   2004

     More details

  • ボールの位置と速度に応じた捕球動作の生成

    高御堂雄三, 益子貴史, 小林隆夫

    情報処理学会第66回(平成16年)全国大会講演論文集   4 ( 3B-6 )   89 - 90   2004

     More details

  • Galatea: 音声対話擬人化エージェント開発キット

    西本卓也, 荒木雅弘, 伊藤克亘, 宇津呂武仁, 甲斐充彦, 河口信夫, 河原達也, 桂田浩一, 小林隆夫, 嵯峨山茂樹, 下平博, 伝康晴, 徳田恵一, 中村哲, 新田恒雄, 坂野秀樹他

    インタラクション2004論文集   27 - 28   2004

     More details

  • HMMに基づくテキスト音声合成への混合励振源モデルとポストフィルタの導入

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会論文誌   J87-D-II ( 8 )   1565 - 1571   2004

     More details

  • コーパスベース音声合成技術の動向[IV] - HMM音声合成方式 -

    小林隆夫, 徳田恵一

    電子情報通信学会誌   87 ( 4 )   322 - 327   2004

     More details

  • Speaking style adaptation using context clustering decision tree for HMM-based speech synthesis

    J Yamagishi, M Tachibana, T Masuko, T Kobayashi

    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS   ICASSP2004 ( I )   5 - 8   2004

     More details

    Language:English  

    Web of Science

    researchmap

  • MLLR adaptation for hidden semi-Markov model based speech synthesis

    Junichi Yamagishi, Takashi Masuko, Takao Kobayashi

    Proc. the 8th International Conference on Spoken Language Processing, CD-ROM   INTERSPEECH 2004 ( WeB1403p.14 )   4 pages   2004

     More details

  • Hidden semi-Markov model based speech synthesis

    Heiga Zen Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proc. the 8th International Conference on Spoken Language Processing, CD-ROM   INTERSPEECH 2004 ( WeC1401o.5 )   4 pages   2004

     More details

  • A style control technique for HMM-based speech synthesis

    Keisuke Miyanaga, Takashi Masuko, Takao Kobayashi

    Proc. the 8th International Conference on Spoken Language Processing, CD-ROM   INTERSPEECH2004 ( Spec4701o.4 )   4 pages   2004

     More details

  • Multi-stage spectral subtraction for enhancement of audio signals

    M Okazaki, T Kunimoto, T Kobayashi

    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PROCEEDINGS   ICASSP2004 ( II )   805 - 808   2004

     More details

    Language:English  

    Web of Science

    researchmap

  • A noise reduction technique for audio signals using Multi stage spectral subtraction

    Masatsugu Okazaki, Toshifumi Kunimoto, Takao Kobayashi

    Proc. the 18th International Congress on Acoustics   ICA2004 ( IV )   3113 - 3114   2004

     More details

  • HMM-based speech synthesis with various speaking styles using model interpolation

    Makoto Tachibana, Junichi, Yamagishi Takashi Masuko, Takao Kobayashi

    Proc. the 2nd International Conference on Speech Prosody   SP2004   413 - 416   2004

     More details

  • HMM-based expressive speech synthesis - Towards TTS with arbitrary speaking styles and emotions

    Junichi Yamagishi, Takashi Masuko, Takao Kobayashi

    Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing, Conference CD-ROM   ( 1.13 )   4 pages   2004

     More details

  • A control metho for realizing various styles in HMM speech synthesis

    Technical Report of IEICE   104 ( SP2004-7 )   35 - 40   2004

     More details

  • A pause modeling technique based on multi-space probability distribution

    Technical Report of IEICE   104 ( SP2004-8 )   41 - 46   2004

     More details

  • Performance evaluation of style adaptation in HSMM-based synthesis

    Proc. the 2004 Autumn Meeting of the Acoustical Society of Japan   I ( 3-2-9 )   333 - 334   2004

     More details

  • HMM parameter reestimation with explicit duration model for HMM-based speech systhesis

    Proc. the 2004 Spring Meeting of the Acoustical Society of Japan   I ( 1-7-6 )   223 - 224   2004

     More details

  • A study on state duration modeling using lognormal distribution for HMM-based speech synthesis

    YAMAGISHI J.

    Proc. the 2004 Spring Meeting of the Acoustical Society of Japan   I ( 1-7-7 )   225 - 226   2004

     More details

  • Incorporation of mixed excitation model and postfilter into HMM-based text-to-speech synthesis

    Trans. IEICE D-II   J87-D-II ( 8 )   1565 - 1571   2004

     More details

  • Technology trends in corpus-based speech synthesis [IV]: HMM-based speech synthesis

    Takao Kobayashi Keiichi Tokuda

    The Journal of the Institute of Electronics, Information and Communication Engineers   87 ( 4 )   322 - 327   2004

     More details

  • MLLR adaptation for hidden semi-Markov model based speech synthesis

    Junichi Yamagishi, Takashi Masuko, Takao Kobayashi

    Proc. the 8th International Conference on Spoken Language Processing, CD-ROM   INTERSPEECH 2004 ( WeB1403p.14 )   4 pages   2004

     More details

  • Hidden semi-Markov model based speech synthesis

    Heiga Zen Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proc. the 8th International Conference on Spoken Language Processing, CD-ROM   INTERSPEECH 2004 ( WeC1401o.5 )   4 pages   2004

     More details

  • A style control technique for HMM-based speech synthesis

    Keisuke Miyanaga, Takashi Masuko, Takao Kobayashi

    Proc. the 8th International Conference on Spoken Language Processing, CD-ROM   INTERSPEECH2004 ( Spec4701o.4 )   4 pages   2004

     More details

  • A noise reduction technique for audio signals using Multi stage spectral subtraction

    Masatsugu Okazaki, Toshifumi Kunimoto, Takao Kobayashi

    Proc. the 18th International Congress on Acoustics   ICA2004 ( IV )   3113 - 3114   2004

     More details

  • HMM-based speech synthesis with various speaking styles using model interpolation

    Makoto Tachibana, Junichi, Yamagishi Takashi Masuko, Takao Kobayashi

    Proc. the 2nd International Conference on Speech Prosody   SP2004   413 - 416   2004

     More details

  • HMM-based expressive speech synthesis - Towards TTS with arbitrary speaking styles and emotions

    Junichi Yamagishi, Takashi Masuko, Takao Kobayashi

    Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing, Conference CD-ROM   ( 1.13 )   4 pages   2004

     More details

  • An HMM-based approach to speaker-dependent 100 bit/s speech coding

    Takahiro Hoshiya, Heiga Zen, Shinji Sako Keiichi, Tokuda Takashi Masuko Takao Kobayashi, Tadashi Kitamura

    Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing, Conference CD-ROM   ( 1.5 )   6 pages   2004

     More details

  • A study on MLLR-based style adaptation in HSMM-based speech synthesis

    Technical Report of IEICE   104 ( SP2004-49 )   13 - 18   2004

     More details

  • Mixture density models based on mel-cepstral representation of Gaussian process

    T Takahashi, K Tokuda, T Kobayashi, T Kitamura

    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES   E86A ( 8 )   1971 - 1978   2003.8

     More details

    Language:English  

    Web of Science

    researchmap

  • A training method of average voice model for HMM-based speech synthesis

    J Yamagishi, M Tamura, T Masuko, K Tokuda, T Kobayashi

    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES   E86A ( 8 )   1956 - 1963   2003.8

     More details

    Language:English  

    Web of Science

    researchmap

  • A context clustering technique for average voice models

    J Yamagishi, M Tamura, T Masuko, K Tokuda, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E86D ( 3 )   534 - 542   2003.3

     More details

    Language:English  

    Web of Science

    researchmap

  • Speaker adaptation using context clustering decision tree for HMM-based speech synthesis

    Technical Report of IEICE   103 ( SP2003-79 )   31 - 36   2003

     More details

  • A study on speaking style adaptation in HMM-based speech synthesis

    Proc. the 2003 Autumn Meeting of the Acoustical Society of Japan   I ( 1-8-29 )   239 - 240   2003

     More details

  • A study on speaker adaptation technique using context clustering decision tree

    Proc. the 2003 Autumn Meeting of the Acoustical Society of Japan   I ( 1-8-16 )   213 - 214   2003

     More details

  • A study on HMM-based hand-gesture synthesis

    Proc. the 65th National Convention of IPSJ   5 ( 3T7A-5 )   407 - 410   2003

     More details

  • 電子楽器用波形符号化方式の検討

    岡崎雅嗣, 岡村和久, 小林隆夫

    電子情報通信学会技術研究報告   103 ( DSP2002-168 )   47 - 52   2003

     More details

  • IFAS-based Voiced/Unvoiced Classification of Speech Signal

    Dhany Arifianto, Takao Kobayashi

    Proc. the 2003 IEEE International Conference on Acoustics, Speech and Signal Processing   ICASSP2003 ( I )   812 - 815   2003

     More details

  • Improving the performance of HMM-based very low bit rate speech coding

    T Hoshiya, S Sako, H Zen, K Tokuda, T Masuko, T Kobayashi, T Kitamura

    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS   ICASSP2003 ( I )   800 - 803   2003

     More details

    Language:English  

    Web of Science

    researchmap

  • HMM音声合成における発話スタイルのモデル化と生成

    大西浩二, 益子貴史, 小林隆夫

    日本音響学会2003年春季研究発表会講演論文集   I ( 1-6-6 )   233 - 234   2003

     More details

  • 信号の非定常性を考慮したスペクトルサブトラクション法

    岡崎雅嗣, 国本利文, 小林隆夫

    電子情報通信学会技術研究報告   103 ( DSP2003-96 )   41 - 46   2003

     More details

  • HMM音声合成におけるモデル補間・適応による発話スタイルの多様化の検討

    橘誠 山岸順一, 大西浩二, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   103 ( SP2003-80 )   37 - 42   2003

     More details

  • HMM音声合成におけるコンテキストクラスタリング決定木を用いた話者適応の検討

    山岸順一, 益子貴史, 徳田恵一, 小林隆夫

    電子情報通信学会技術研究報告   103 ( SP2003-79 )   31 - 36   2003

     More details

  • 声道長正規化を用いた平均声モデル学習の検討

    広畑誠, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   103 ( SP2003-19 )   69 - 75   2003

     More details

  • 擬人化音声対話エージェントツールキット Galatea

    嵯峨山茂樹, 川本真一, 下平博, 新田恒雄, 西本卓也, 中村哲, 伊藤克亘, 森島繁生, 四倉達夫, 甲斐充彦, 李晃伸, 山下洋一, 小林隆夫, 徳田恵一, 広瀬啓吉, 峯松信明他

    情報処理学会研究報告   2003 ( SLP-45-10 )   57 - 64   2003

     More details

  • HMM音声合成における異なる発話スタイル生成の検討

    大西浩二, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   103 ( SP2002-172 )   17 - 22   2003

     More details

  • A study on average voice model training using vocal tract length normalization

    Technical Report of IEICE   103 ( SP2003-19 )   69 - 75   2003

     More details

  • Galatea: An anthropomorphic spoken dialogue agent toolkit

    IPSJ SIG Notes   2003 ( SLP-45-10 )   57 - 64   2003

     More details

  • A study on HMM-based speech synthesis with various speaking styles

    Technical Report of IEICE   103 ( SP2002-172 )   17 - 22   2003

     More details

  • Audio coding for digital musical instruments

    Technical Report of IEICE   103 ( DSP2002-168 )   47 - 52   2003

     More details

  • IFAS-based voiced/unvoiced classification of speech signal

    D Arifianto, T Kobayashi

    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS   ICASSP2003 ( I )   812 - 815   2003

     More details

    Language:English  

    Web of Science

    researchmap

  • Performance evaluation of IFAS-based fundamental frequency estimator in noisy environments

    Dhany Arifianto, Takao Kobayashi

    Proc. the 8th Eurpean Conference on Speech Communication and Technology   EUROSPEECH03 ( IV )   2877 - 2880   2003

     More details

  • Modeling of various speaking styles and emotions for HMM-based speech synthesis

    Junichi Yamagishi, Koji Onishi, Takashi Masuko, Takao Kobayashi

    Proc. the 8th Eurpean Conference on Speech Communication and Technology   EUROSPEECH03 ( III )   2461 - 2464   2003

     More details

  • Normalized training for HMM-based visual speech recognition

    Trans. IEICE D-II   J86-D-II ( 2 )   163 - 172   2003

     More details

  • Spectral subtraction of nonstationary audio signals for noise reduction

    Technical Report of IEICE   103 ( DSP2003-96 )   41 - 46   2003

     More details

  • HMM-based synthesis of human arm motion

    Proc. the 65th National Convention of IPSJ   5 ( 3T7A-4 )   403 - 406   2003

     More details

  • Audio indexing for speech, music, and mixed sounds

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 3-6-11 )   340 - 350   2003

     More details

  • Voiced/Unvoiced decision using harmonicity measure

    Dhany Arifianto, Takao Kobayashi

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 3-6-7 )   341 - 342   2003

     More details

  • The scheme to create codebooks using decision tree in HMM-based very low bit rate speech coding

    HOSHIYA Takahiro, SAKO Shinji, ZEN Heiga, TOKUDA Keiichi, MASUKO Takashi, KOBAYASHI Takao, KITAMURA Tadashi

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 3-3-14 )   323 - 324   2003

     More details

    Language:Japanese  

    CiNii Books

    researchmap

  • A study on adaptation technique for speech synthesis with arbitrary speaker's voice and various speaking styles

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 1-6-25 )   271 - 272   2003

     More details

  • A study on HMM-based emotional speech synthesis

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 1-6-24 )   269 - 270   2003

     More details

  • Automatic estimation of postfilter coefficients for HMM-based speech synthesis

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 1-6-11 )   243 - 244   2003

     More details

  • Modeling and generation of various speaking styles in HMM-based speech synthesis

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 1-6-6 )   233 - 234   2003

     More details

  • HMM-based speech synthesis with various speaking styles using model interpolation and adaptation

    Technical Report of IEICE   103 ( SP2003-80 )   37 - 42   2003

     More details

  • Average voice model for synthesizing speech with arbitrary speaker's voice

    Takao Kobayashi Junichi Yamagishi, Takashi Masuko

    Proc. 2002 2nd Plenary Meeting and Symposium on Prosody and Speech Processing   63 - 68   2003

     More details

  • 極低ビットレート音声符号化システムにおける決定木を用いたコードブックの自動決定

    星屋剛宏, 酒向慎司, 全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2003年春季研究発表会講演論文集   I ( 3-3-14 )   323 - 324   2003

     More details

  • 多様な声質・発話スタイルによる音声合成のための適応手法の検討

    山岸順一, 大西浩二, 益子貴史, 小林隆夫

    日本音響学会2003年春季研究発表会講演論文集   I ( 1-6-25 )   271 - 272   2003

     More details

  • HMM音声合成における感情表現のモデル化に関する検討

    都築亮介, 全炳河, 徳田恵一, 北村正, 益子貴史, 小林隆夫

    日本音響学会2003年春季研究発表会講演論文集   I ( 1-6-24 )   269 - 270   2003

  • HMM音声合成のためのポストフィルタ係数の自動決定

    岸本由加, 全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2003年春季研究発表会講演論文集   I ( 1-6-11 )   243 - 244   2003

     More details

  • HMMからの尤度最大基準に基づく条件つきパラメータ生成の検討

    益子貴史, 徳田恵一, 小林隆夫

    日本音響学会2003年秋季研究発表会講演論文集   I ( 1-8-14 )   209 - 210   2003

     More details

  • HMM音声合成における発話スタイルの制御

    山岸順一, 大西浩二, 益子貴史, 小林隆夫

    情報処理学会第65回(平成15年)全国大会講演論文集   5 ( 5T7B-5 )   511 - 514   2003

     More details

  • 隠れマルコフモデルに基づくハンドジェスチャー生成の検討

    高御堂雄三, 羽岡哲郎, 益子貴史, 小林隆夫

    情報処理学会第65回(平成15年)全国大会講演論文集   5 ( 3T7A-5 )   407 - 410   2003

     More details

  • 隠れマルコフモデルに基づく腕の動きの生成

    吉岡元貴, 益子貴史, 小林隆夫

    情報処理学会第65回(平成15年)全国大会講演論文集   5 ( 3T7A-4 )   403 - 406   2003

     More details

  • 音声と音楽およびその混合音のインデキシング

    今井田誠治, 益子貴史, 小林隆夫

    日本音響学会2003年春季研究発表会講演論文集   I ( 3-6-11 )   340 - 350   2003

     More details

  • Voiced/Unvoiced decision using harmonicity measure

    Dhany Arifianto, Takao Kobayashi

    Proc. the 2003 Spring Meeting of the Acoustical Society of Japan   I ( 3-6-7 )   341 - 342   2003

     More details

  • 擬人化音声対話エージェント基本ソフトウェアの開発プロジェクト報告

    嵯峨山茂樹, 伊藤克亘, 宇津呂武仁, 甲斐充彦, 小林隆夫, 下平博, 伝康晴, 徳田恵一, 中村哲, 西本卓也, 新田恒雄, 広瀬啓吉, 峯松信明, 森島繁生, 山下洋一, 山田篤他

    情報処理学会研究報告   2003 ( SLP-49-56 )   319 - 324   2003

     More details

  • Average voice model for synthesizing speech with arbitrary speaker's voice

    Takao Kobayashi Junichi Yamagishi, Takashi Masuko

    Proc. 2002 2nd Plenary Meeting and Symposium on Prosody and Speech Processing   63 - 68   2003

     More details

  • HMM音声合成における異なる発話スタイルへの適応の検討

    橘誠 山岸順一, 益子貴史, 小林隆夫

    日本音響学会2003年秋季研究発表会講演論文集   I ( 1-8-29 )   239 - 240   2003

     More details

  • コンテキストクラスタリング決定木を用いた話者適応の検討

    山岸順一, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2003年秋季研究発表会講演論文集   I ( 1-8-16 )   213 - 214   2003

     More details

  • A study on conditional parameter generation from HMM based on maximum likelihood criterion

    Proc. the 2003 Autumn Meeting of the Acoustical Society of Japan   I ( 1-8-14 )   209 - 210   2003

     More details

  • Speaking styles control in HMM-based speech synthesis

    Proc. the 65th National Convention of IPSJ   5 ( 5T7B-5 )   511 - 514   2003

     More details

  • A training method for average voice model based on shared decision tree context clustering and speaker adaptive training

    J Yamagishi, T Masuko, K Tokuda, T Kobayashi

    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS   ICASSP2003 ( I )   716 - 719   2003

     More details

    Language:English  

    Web of Science

    researchmap

  • Performance evaluation of IFAS-based fundamental frequency estimator in noisy environments

    ARIFIANTO D.

    Proc. EUROSPEECH'03, Geneva, Switzerland, Sept.   EUROSPEECH03 ( IV )   2877 - 2880   2003

     More details

  • Modeling of various speaking styles and emotions for HMM-based speech synthesis

    Junichi Yamagishi, Koji Onishi, Takashi Masuko, Takao Kobayashi

    Proc. the 8th Eurpean Conference on Speech Communication and Technology   EUROSPEECH03 ( III )   2461 - 2464   2003

     More details

  • 隠れマルコフモデルを用いた視覚音声認識のための正規化学習

    南角吉彦, 徳田恵一, 北村正, 小林隆夫

    電子情報通信学会論文誌   J86-D-II ( 2 )   163 - 172   2003

     More details

  • Development of anthropomophic spoken dialogue agent toolkit

    IPSJ SIG Notes   2003 ( SLP-49-56 )   319 - 324   2003

     More details

  • Speech synthesis with arbitrary speaker's voice from average voice - Speaker adaptation of F0 and spectrum for HMM-based speech synthesis

    Takao Kobayashi, Masatsune Tamura, Takashi Masuko

    Proc. Symposium on Prosody and Speech Processing   163 - 168   2002

     More details

  • HMMに基づく音声合成におけるピッチ・スペクトルの話者適応

    田村正統, 益子貴史, 徳田恵一, 小林隆夫

    電子情報通信学会誌   J85-D-II ( 4 )   545 - 553   2002

     More details

  • Eigenvoices for HMM-based speech synthesis

    Kengo Shichiri, Atsushi Sawabe, Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proc. 7th International Conference on Spoken Language Processing   ICSLP2002 ( 2 )   1269 - 1272   2002

     More details

  • A context clustering technique for average voice model in HMM-based speech synthesis

    Junichi Yamagishi, Masatsune Tamura, Takashi Masuko Keiichi Tokuda, Takao Kobayashi

    Proc. 7th International Conference on Spoken Language Processing   ICSLP2002 ( 1 )   133 - 136   2002

     More details

  • Very low bit rate speech coding based on HMM with speaker adaptation

    Trans. IEICE D-II   J85-D-II ( 12 )   1749 - 1759   2002

     More details

  • Open-source software for developing anthropomorphic spoken dialog agents

    S. Kawamoto, H, Shimodaira, T. Nitta, T. Nishimoto, S. Nakamura, K. Itou, S. Morishima T. Yotsukura, A. Kai, A. Lee, Y, Yamashita T, Kobayashi

    Proc. International Workshop on Lifelike Animated Agents, Tools, Affective Functions, and Applications   64 - 69   2002

     More details

  • 動的特徴量を考慮した統計的尺度に基づくメルケプストラム係数のベクトル量子化

    高橋徹, 徳田恵一, 小林隆夫, 北村正

    日本音響学会2002年春季研究発表会講演論文集   I ( 1-P-1 )   353 - 354   2002

     More details

  • ウェアラブルコンピュータとコンパニオンロボットによるBluetoothを利用した動画像通信とインタラクション

    三浦和人, 小林隆夫, 竹林洋一

    情報処理学会第64回(平成14年)全国大会講演論文集   4 ( 6V-02 )   103 - 104   2002

     More details

  • Fundamental frequency estimation based on instantaneous frequency amplitude spectrum

    T Tanaka, T Kobayashi, D Arifianto, T Masuko

    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS   ICASSP2002 ( I )   329 - 332   2002

     More details

    Language:English  

    Web of Science

    researchmap

  • HMMを用いた音声合成における学習データ量と音質の調査

    高御堂雄三, 徳田恵一, 北村正, 益子貴史, 小林隆夫

    日本音響学会2002年春季研究発表会講演論文集   I ( 2-10-14 )   291 - 292   2002

     More details

  • Speech synthesis with arbitrary speaker's voice from average voice - Speaker adaptation of F0 and spectrum for HMM-based speech synthesis

    Takao Kobayashi, Masatsune Tamura, Takashi Masuko

    Proc. Symposium on Prosody and Speech Processing   163 - 168   2002

     More details

  • 擬人化音声対話エージェントツールキットの基本設計

    川本真一, 下平博, 新田恒雄, 西本卓也, 中村哲, 伊藤克亘, 森島繁生, 四倉達夫, 甲斐充彦, 李晃伸, 山下洋一, 小林隆夫, 徳田恵一, 広瀬啓吉, 峯松信明, 山田篤, 伝康晴, 宇津呂武仁, 他

    情報処理学会研究報告   2002-SLP-40-11   61 - 66   2002

     More details

  • 隠れマルコ不モデルに基づくハンドジェスチャーアニメーション生成

    羽岡哲郎, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   102 ( IE2002-129 )   43 - 48   2002

     More details

  • 平均声モデル構築のためのコンテキストクラスタリング手法の検討

    山岸順一, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    電子情報通信学会技術研究報告   102 ( SP2002-28 )   25 - 30   2002

     More details

  • マルチモーダルコミュニケーションのための音声合成プラットホーム

    山下洋一, 喜多竜二, 峯松信明, 吉村貴克, 徳田恵一, 田村正統, 益子貴史, 小林隆夫, 広瀬啓吉

    情報処理学会研究報告   2002-SLP-40-12   67 - 72   2002

     More details

  • A Study on Context Clustering Techniques and Speaker Adaptive Training for Average Voice Model

    YAMAGISHI Junichi, TAMURA Masatsune, MASUKO Takashi, KOBAYASHI Takao, TOKUDA Keiichi

    IEICE technical report. Speech   102 ( SP2002-72 )   5 - 10   2002

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    This paper describes a new training method of average voice model for speech synthesis using speaker adaptation. When the amount of training data is limited, it would occur that the distributions of average voice model have bias depending on speaker and/or gender. In the proposed method, to reduce the influence of speaker dependence, we incorporate a context clustering technique called shared decision tree context clustering and speaker adaptive training into the training procedure of average voice model. From the results of subjective tests, we show that the average voice model trained using the proposed method can generate more natural sounding speech than the conventional average voice model. Moreover, it is shown that voice characteristics of synthetic speech generated from the adapted model using the proposed method is closer to the target speaker's voice than the conventional method.

    CiNii Books

    researchmap

  • 擬人化音声対話エージェント開発プロジェクト (招待講演)

    嵯峨山茂樹, 伊藤克亘, 宇津呂武仁, 甲斐充彦, 小林隆夫, 下平博, 伝康晴, 徳田恵一, 中村哲, 西本卓也, 新田恒雄, 広瀬啓吉, 森島繁生, 峯松信明, 山下洋一, 山田篤, 李晃伸

    日本音響学会2002年春季研究発表会講演論文集   I ( 1-5-14 )   27 - 28   2002

     More details

  • 擬人化音声対話エージェントにおける音声合成

    山下洋一, 峯松信明, 徳田恵一, 小林隆夫, 広瀬啓吉

    日本音響学会2002年春季研究発表会講演論文集   I ( 1-5-17 )   33 - 34   2002

     More details

  • 話者適応のための平均声モデル学習法の評価

    山岸順一, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2002年秋季研究発表会講演論文集   I ( 3-10-13 )   353 - 354   2002

     More details

  • 固有声を用いたHMM音声合成における声質評価

    七里建吾, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2002年秋季研究発表会講演論文集   I ( 3-10-16 )   359 - 360   2002

     More details

  • HMM音声合成のためのポストフィルタリング

    岸本由加, 全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2002年秋季研究発表会講演論文集   I ( 2-1-1 )   279 - 280   2002

     More details

  • 話者適応のための平均声モデル学習法の検討

    山岸順一, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2002年秋季研究発表会講演論文集   I ( 3-10-12 )   351 - 352   2002

     More details

  • HMMに基づいた極低ビットレート音声符号化システムの性能改善

    星屋剛宏, 酒向慎司, 全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2002年秋季研究発表会講演論文集   I ( 1-10-3 )   229 - 230   2002

     More details

  • HMM音声合成におけるSATを用いた平均声モデルの学習

    田村正統, 益子貴史, 徳田恵一, 小林隆夫

    日本音響学会2002年春季研究発表会講演論文集   I ( 1-10-17 )   263 - 264   2002

     More details

  • HMM音声合成におけるコンテキストクラスタリング決定木の構築法の検討

    山岸順一, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2002年春季研究発表会講演論文集   I ( 1-10-1 )   231 - 232   2002

     More details

  • 部分的共有を行ったHMMからの音声合成

    全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2002年春季研究発表会講演論文集   I ( 1-10-3 )   235 - 236   2002

     More details

  • Open-source software for developing anthropomorphic spoken dialog agents

    S. Kawamoto, H, Shimodaira, T. Nitta, T. Nishimoto, S. Nakamura, K. Itou, S. Morishima T. Yotsukura, A. Kai, A. Lee, Y, Yamashita T, Kobayashi

    Proc. International Workshop on Lifelike Animated Agents, Tools, Affective Functions, and Applications   64 - 69   2002

     More details

  • Eigenvoices for HMM-based speech synthesis

    Kengo Shichiri, Atsushi Sawabe, Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proc. 7th International Conference on Spoken Language Processing   ICSLP2002 ( 2 )   1269 - 1272   2002

     More details

  • スペクトル分析のための尺度を用いたメルケプストラム係数のベクトル量子化

    高橋徹, 徳田恵一, 小林隆夫, 北村正

    電子情報通信学会論文誌   J85-D-II ( 8 )   1273 - 1283   2002

     More details

  • HMMに基づいた極低ビットレート音声符号化における不特定話者への対応

    益子貴史, 徳田恵一, 小林隆夫

    電子情報通信学会論文誌   J85-D-II ( 12 )   1749 - 1759   2002

     More details

  • HMMに基づいた視聴覚テキスト音声合成 - 画像ベースアプローチ

    酒向慎司, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    情報処理学会論文誌   43 ( 7 )   2169 - 2176   2002

     More details

  • 話者照合におけるHMM音声合成による合成音声の判別

    佐藤隆之, 益子貴史, 小林隆夫, 徳田恵一

    情報処理学会論文誌   43 ( 7 )   2197 - 2204   2002

     More details

  • Multi-space probability distribution HMM (Invited paper)

    Keiichi Tokuda, Takashi Mausko Noboru, Miyazaki, Takao Kobayashi

    IEICE Trans. Information and Systems   E85-D ( 3 )   455 - 464   2002

     More details

  • カスタマイズ性を考慮した擬人化音声対話ソフトウェアツールキットの設計

    川本真一, 下平博, 新田恒雄, 西本卓也, 中村哲, 伊藤克亘, 森島繁生, 四倉達夫, 甲斐充彦, 李晃伸, 山下洋一, 小林隆夫, 徳田恵一, 広瀬啓吉, 峯松信明, 山田篤, 伝康晴, 宇津呂武仁, 他

    情報処理学会論文誌   43 ( 7 )   2249 - 2263   2002

     More details

  • A context clustering technique for average voice model in HMM-based speech synthesis

    Junichi Yamagishi, Masatsune Tamura, Takashi Masuko Keiichi Tokuda, Takao Kobayashi

    Proc. 7th International Conference on Spoken Language Processing   ICSLP2002 ( 1 )   133 - 136   2002

     More details

  • Multi-space probability distribution HMM (Invited paper)

    Keiichi Tokuda, Takashi Mausko Noboru, Miyazaki, Takao Kobayashi

    IEICE Trans. Information and Systems   E85-D ( 3 )   455 - 464   2002

     More details

  • Speaker Adaptation of Pitch and Spectrum for HMM-Based Speech Synthesis

    Trans. IEICE D-II   J85-D-II ( 4 )   545 - 553   2002

     More details

  • Vector quantization of mel-cepstral coefficients using distortion measure for spectral analysis

    Trans. IEICE D-II   J85-D-II ( 8 )   1273 - 1283   2002

     More details

  • Discrimination of synthetic speech generated by an HMM-based speech synthesis system for speaker verification

    IPSJ Journal   43 ( 7 )   2197 - 2204   2002

     More details

  • HMM-based audio-visual speech synthesis ― Pixel-based approach

    IPSJ Journal   43 ( 7 )   2169 - 2176   2002

     More details

  • Design of software toolkit for anthropomorphic spoken dialog agent software with customization-oriented features

    IPSJ Journal   43 ( 7 )   2249 - 2263   2002

     More details

  • Vector quantization of speech spectral parameters using statistics of static and dynamic features

    K Koishida, K Tokuda, T Masuko, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E84D ( 10 )   1427 - 1434   2001.10

     More details

    Language:English  

    Web of Science

    researchmap

  • Text-independent speaker identification using Gaussian mixture models based on multi-space probability distribution

    C Miyajima, Y Hattori, K Tokuda, T Masuko, T Kobayashi, T Kitamura

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E84D ( 7 )   847 - 855   2001.7

     More details

    Language:English  

    Web of Science

    researchmap

  • Mixed excitation for HMM-based speech synthesis

    Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proc. 7th European Conference on Speech Communication and Technology   EUROSPEECH 2001 ( 3 )   2259 - 2262   2001

     More details

  • ソース・フィルタ理論

    小林隆夫

    日本音響学会誌   57 ( 1 )   65   2001

     More details

  • 動的特徴量を考慮したピッチの高精度モデル化手法

    全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2001年秋季研究発表会講演論文集   1-2-7   219 - 220   2001

     More details

  • スペクトル分析のための基準を用いたHMMの学習アルゴリズム

    高橋徹, 徳田恵一, 小林隆夫, 北村正

    日本音響学会2001年秋季研究発表会講演論文集   1-1-3   5 - 6   2001

     More details

  • HMM音声合成に用いるコンテキストの検討

    吉岡元貴, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2001年秋季研究発表会講演論文集   3-2-5   313 - 314   2001

     More details

  • HMM音声合成のためのガンマ分布を用いた状態継続長のモデル化

    石松喜伸, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2001年秋季研究発表会講演論文集   3-2-4   311 - 312   2001

     More details

  • HMMに基づく音声合成システムにおける音韻継続長の話者適応

    田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2001年秋季研究発表会講演論文集   3-2-7   317 - 318   2001

     More details

  • 固有声に基づいた音声合成おけるピッチのモデル化

    沢部敦, 七里建吾, 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2001年秋季研究発表会講演論文集   3-2-6   315 - 316   2001

     More details

  • MM音声合成における平均声モデルの学習セットの検討

    山岸順一, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2001年秋季研究発表会講演論文集   3-2-10   323 - 324   2001

     More details

  • HMM音声合成システムのためのテキスト処理部の構築

    熊倉俊之, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2001年春季研究発表会講演論文集   3-Q-4   349 - 350   2001

     More details

  • HMM音声合成におけるMLLRを用いたピッチ・スペクトルの話者適応

    田村正統, 益子貴史, 徳田恵一, 小林隆夫

    電子情報通信学会技術研究報告   SP2001-11   15 - 20   2001

     More details

  • 瞬時周波数振幅スペクトルに基づくピッチ抽出法の検討

    田中智宏, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   SP2000-160   1 - 8   2001

     More details

  • HMM音声合成おけるスペクトル・ピッチへの固有声手法の適用

    沢部敦, 七里建吾, 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP2001-72   65 - 72   2001

     More details

  • 不特定話者対応HMM認識ボコーダの検討

    益子貴史, 小林隆夫, 徳田恵一

    電子情報通信学会技術研究報告   SP2001-37   9 - 16   2001

     More details

  • HMMに基づく音声合成への混合励振源モデルとポストフィルタの導入

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP2001-63   17 - 22   2001

     More details

  • 有声/無声境界の動的特徴量を考慮したピッチのモデル化

    全炳河, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP2001-70   53 - 58   2001

     More details

  • HMM音声合成における韻律の変動要因用の検討

    吉岡元貴, 田村正統, 益子貴史, 小林隆夫, 徳田恵一

    電子情報通信学会技術研究報告   SP2001-80   51 - 56   2001

     More details

  • HMM音声合成におけるガンマ分布状態継続長モデルの検討

    石松喜伸, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP2001-81   57 - 62   2001

     More details

  • 合成音声に対する安全性を考慮したテキスト指定型話者照合システムの検討

    佐藤隆之, 益子貴史, 小林隆夫, 徳田恵一

    電子情報通信学会技術研究報告   SP2001-79   45 - 50   2001

     More details

  • バイモーダル音声データベースの構築

    堤啓児, 益子貴史, 小林隆夫

    日本音響学会2001年秋季研究発表会講演論文集   1-P-12   379 - 380   2001

     More details

  • HMMに基づく音声合成における品質改善に関する検討

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2001年秋季研究発表会講演論文集   1-P-8   371 - 372   2001

     More details

  • 合成音声に対する安全性を考慮したテキスト指定型話者照合システムの検討

    佐藤隆之, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2001年春季研究発表会講演論文集   1-3-4   7 - 8   2001

     More details

  • 不特定話者対応HMM認識ボコーダに関する検討

    日小田芳郎, 益子貴史, 小林隆夫, 徳田恵一

    電子情報通信学会2001年総合大会講演論文集   情報・システム ( 1 )   191   2001

     More details

  • 唇動画像と音声によるマルチモーダルデータベースの構築

    酒向慎司, 近藤重一, 益子貴史, 徳田恵一, 小林隆夫, 北村正

    日本音響学会2001年春季研究発表会講演論文集   3-P-30   223 - 224   2001

     More details

  • 音声のメルケプストラム表現に基づいたGMM

    高橋徹, 徳田恵一, 小林隆夫, 北村正

    日本音響学会2001年春季研究発表会講演論文集   3-3-9   111 - 112   2001

     More details

  • 混合励振源を用いた低ビットレート音声符号化の品質向上の検討

    廣谷定男, 益子貴史, 小林隆夫

    日本音響学会2001年春季研究発表会講演論文集   1-6-23   273 - 274   2001

     More details

  • HMMに基づく音声合成システムにおけるピッチ・スペクトルの話者適応

    田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2001年春季研究発表会講演論文集   1-6-2   2001

     More details

  • 固有声に基づいたtriphoneによる音声合成

    沢部敦, 七里建吾, 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2001年春季研究発表会講演論文集   2-6-9   299 - 301   2001

     More details

  • HMMに基づく音声合成のための励振源モデルの検討

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2001年春季研究発表会講演論文集   2-6-8   2001

     More details

  • A design of anthropomorphic spoken dialog agent for high interactivity

    SIG-SLUD-A102-12   63 - 68   2001

     More details

  • Data analysis of corrosion signals using the thin film ECT probe for copper pipe inspections

    2001   55 - 56   2001

     More details

  • Text-to-speech synthesis with arbitrary speaker's voice from average voice

    Masatsune Tamura, Takashi Masuko Keiichi Tokuda, Takao Kobayashi

    Proc. 7th European Conference on Speech Communication and Technology   EUROSPEECH 2001 ( 1 )   345 - 348   2001

     More details

  • Mixed excitation for HMM-based speech synthesis

    Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proc. 7th European Conference on Speech Communication and Technology   EUROSPEECH 2001 ( 3 )   2259 - 2262   2001

     More details

  • Speaker identification using Gaussian mixture models based on multi-space probability distribution

    C Miyajima, Y Hattori, K Tokuda, T Masuko, T Kobayashi, T Kitamura

    2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS   ICASSP 2001 ( I )   433 - 436   2001

     More details

    Language:English  

    Web of Science

    researchmap

  • Text-to-speech synthesis with arbitrary speaker's voice from average voice

    Masatsune Tamura, Takashi Masuko Keiichi Tokuda, Takao Kobayashi

    Proc. 7th European Conference on Speech Communication and Technology   EUROSPEECH 2001 ( 1 )   345 - 348   2001

     More details

  • A robust speaker verification system against imposture using an HMM-based speech synthesis

    Takayuki Satoh, Takashi Masuko, Takao Kobayashi Keiichi Tokuda

    Proc. 7th European Conference on Speech Communication and Technology   EUROSPEECH 2001 ( 2 )   759 - 762   2001

     More details

  • インタラクティブ性を重視した擬人化音声対話エージェントの基本設計

    川本真一, 下平博, 嵯峨山茂樹, 新田恒雄, 西本卓也, 中村哲, 伊藤克亘, 森島繁生, 四倉達夫, 甲斐充彦, 李晃伸, 山下洋一, 小林隆夫, 徳田恵一, 広瀬啓吉, 峯松信明

    人工知能学会研究会資料   SIG-SLUD-A102-12   63 - 68   2001

     More details

  • 渦流探傷センサによる銅配管腐食評価手法の検討

    篠澤康彦, 安倍健, 小林隆夫, 市村岳

    日本非破壊検査協会平成13年度春季講演会論文集   2001   55 - 56   2001

     More details

  • Speaker identification using Gaussian mixture models based on multi-space probability distribution

    Chiyomi Miyajima, Yosuke Hattori, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   1 ( I )   433 - 436   2001

     More details

  • Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR

    M Tamura, T Masuko, K Tokuda, T Kobayashi

    2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS   ICASSP 2001 ( II )   805 - 808   2001

     More details

    Language:English  

    Web of Science

    researchmap

  • A robust speaker verification system against imposture using an HMM-based speech synthesis

    Takayuki Satoh, Takashi Masuko, Takao Kobayashi Keiichi Tokuda

    Proc. 7th European Conference on Speech Communication and Technology   EUROSPEECH 2001 ( 2 )   759 - 762   2001

     More details

  • A 16kb/s wideband CELP-based speech coder using mel-generalized cepstral analysis

    K Koishida, G Hirabayashi, K Tokuda, T Kobayashi

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E83D ( 4 )   876 - 883   2000.4

     More details

    Language:English  

    Web of Science

    researchmap

  • Pitch Pattern Generation Using Multi-Space Probability Distribution HMM

    MASUKO Takashi, TOKUDA Keiichi, MIYAZAKI Noboru, KOBAYASHI Takao

    Trans IEICE D-II   J83-D-II ( 7 )   1600 - 1609   2000

     More details

    Language:Japanese   Publisher:Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1476/00004832/

  • Vector Quantization of Mel-cepstral Coefficients Based on a Statistical Measure

    Tohru Takahashi, Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura

    Proc. 2000 IEEE International Symposium on Intelligent Signal Processing and Communication Systems   ISPACS 2000   692 - 695   2000

     More details

  • HMM-Based Text-to-Audio-Visual Speech Synthesis

    Shinji Sako, Keiichi Tokuda, Takashi Masuko Takao Kobayashi, Tadashi Kitamura

    Proc. 6th International Conference on Spoken Language Processing   ICSLP 2000 ( III )   25 - 28   2000

     More details

  • Imposture Using Synthetic Speech against Speaker Verification Based on Spectrum and Pitch

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

    Proc. 6th International Conference on Spoken Language Processing   ICSLP 2000 ( II )   302 - 305   2000

     More details

  • Speech parameter generation algorithms for HMM-based speech synthesis

    K Tokuda, T Yoshimura, T Masuko, T Kobayashi, T Kitamura

    2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI   ICASSP 2000 ( III )   1315 - 1318   2000

     More details

    Language:English  

    Web of Science

    researchmap

  • Normalized training for HMM-based visual speech recognition

    Y Nankaku, K Tokuda, T Kitamura, T Kobayashi

    2000 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS   ICIP 2000 ( 3 )   234 - 237   2000

     More details

    Language:English  

    Web of Science

    researchmap

  • HMMに基づく音声合成におけるスペクトル・ピッチ・継続長の同時モデル化

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会論文誌   J83-D-II ( 11 )   2099 - 2107   2000

     More details

  • 話者照合システムに対する合成音声による詐称

    益子貴史, 徳田恵一, 小林隆夫

    電子情報通信学会論文誌   J83-D-II ( 11 )   2283 - 2290   2000

     More details

  • 多空間上の確率分布に基づいたHMM

    徳田恵一, 益子貴史, 宮崎昇, 小林隆夫

    電子情報通信学会論文誌   J83-D-II ( 7 )   1579 - 1589   2000

     More details

  • 多空間確率分布HMMによるピッチパターン生成

    益子貴史, 徳田恵一, 宮崎昇, 小林隆夫

    電子情報通信学会論文誌   J83-D-II ( 7 )   1600 - 1609   2000

     More details

  • Speaker interpolation for HMM-based speech synthesis system.

    Yoshimura Takayoshi, Tokuda Keiichi, Masuko Takashi, Kobayashi Takao, Kitamura Tadashi

    Acoustical Science and Technology   21 ( 4 )   199 - 206   2000

     More details

    Language:English   Publisher:Acoustical Society of Japan  

    This paper describes an approach to voice characteristics conversion for an HMM-based text-to-speech synthesis system using speaker interpolation.Although most text-to-speech synthesis systems which synthesize speech by concatenating speech units can synthesize speech with acceptable quality, they still cannot synthesize speech with various voice quality such as speaker individualities and emotions;In order to control speaker individualities and emotions, therefore, they need a large database, which records speech units with various voice characteristics in sythesis phase.On the other hand, our system synthesize speech with untrained speaker's voice quality by interpolating HMM parameters among some representative speakers' HMM sets.Accordingly, our system can synthesize speech with various voice quality without large database in synthesis phase.An HMM interpolation technique is derived from a probabilistic similarity measure for HMMs, and used to synthesize speech with untrained speaker's voice quality by interpolating HMM parameters among some representative speakers' HMM sets.The results of subjective experiments show that we can gradually change the voice quality of synthesized speech from one's to the other's by changing the interpolation ratio.

    DOI: 10.1250/ast.21.199

    researchmap

  • Speaker Interpolation for HMM-based Speech Synthesis System

    Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    J. Acoust. Soc. Jpn. (E)   21 ( 4 )   199 - 206   2000

     More details

    Language:English   Publisher:Acoustical Society of Japan  

    This paper describes an approach to voice characteristics conversion for an HMM-based text-to-speech synthesis system using speaker interpolation.Although most text-to-speech synthesis systems which synthesize speech by concatenating speech units can synthesize speech with acceptable quality, they still cannot synthesize speech with various voice quality such as speaker individualities and emotions;In order to control speaker individualities and emotions, therefore, they need a large database, which records speech units with various voice characteristics in sythesis phase.On the other hand, our system synthesize speech with untrained speaker's voice quality by interpolating HMM parameters among some representative speakers' HMM sets.Accordingly, our system can synthesize speech with various voice quality without large database in synthesis phase.An HMM interpolation technique is derived from a probabilistic similarity measure for HMMs, and used to synthesize speech with untrained speaker's voice quality by interpolating HMM parameters among some representative speakers' HMM sets.The results of subjective experiments show that we can gradually change the voice quality of synthesized speech from one's to the other's by changing the interpolation ratio.

    DOI: 10.1250/ast.21.199

    researchmap

  • Vector Quantization of Mel-cepstral Coefficients Based on a Statistical Measure

    Tohru Takahashi, Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura

    Proc. 2000 IEEE International Symposium on Intelligent Signal Processing and Communication Systems   ISPACS 2000   692 - 695   2000

     More details

  • Voice Characteristics Conversion for HMM-Based Speech Synthesis System Using MAP-VFS

    Trans. IEICE D-II   83-D-II ( 12 )   2509 - 2516   2000

     More details

  • HMM-Based Text-to-Audio-Visual Speech Synthesis

    Shinji Sako, Keiichi Tokuda, Takashi Masuko Takao Kobayashi, Tadashi Kitamura

    Proc. 6th International Conference on Spoken Language Processing   ICSLP 2000 ( III )   25 - 28   2000

     More details

  • Imposture Using Synthetic Speech against Speaker Verification Based on Spectrum and Pitch

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

    Proc. 6th International Conference on Spoken Language Processing   ICSLP 2000 ( II )   302 - 305   2000

     More details

  • Speech parameter generation algorithms for HMM-based speech synthesis

    Keiichi Tokuda, Takayoshi Yoshimura, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   3 ( III )   1315 - 1318   2000

     More details

    Language:English   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.1109/ICASSP.2000.861820

    Scopus

    researchmap

  • Normalized Training for HMM-Based Visual Speech Recognition

    Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Takao Kobayashi

    Proc. IEEE International Conference on Image Processing   ICIP 2000 ( 3 )   234 - 237   2000

     More details

  • Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis

    Trans. IEICE D-II   J83-D-II ( 11 )   2099 - 2107   2000

     More details

  • Imposture against a Speaker Verification System Using Synthetic Speech

    Trans. IEICE D-II   J83-D-II ( 11 )   2283 - 2290   2000

     More details

  • Multi-Space Probability Distribution HMM

    Trans. IEICE D-II   J83-D-II ( 7 )   1579 - 1589   2000

     More details

  • スペクトルとピッチに基づく話者照合に対する合成音声による詐称

    益子貴史, 徳田恵一, 小林隆夫

    日本音響学会2000年春季研究発表会講演論文集   3-9-4   101 - 102   2000

     More details

  • HMMに基づく音声合成システムにおけるMAP-VFSを用いた声質変換

    益子貴史, 田村正統, 徳田恵一, 小林隆夫

    電子情報通信学会論文誌   83-D-II ( 12 )   2509 - 2516   2000

     More details

  • HMMに基づいた音声・唇動画像の同時生成 - 画像ベースアプローチ -

    酒向慎司, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2000年秋季研究発表会講演論文集   1-Q-3   235 - 236   2000

     More details

  • メル一般化ケプストラム分析に基づくMELP音声符号化

    石松喜伸, 徳田恵一, 北村正, 小林隆夫

    電子情報通信学会2000年基礎・境界ソサイエティ大会講演論文集   A-6-4   153   2000

     More details

  • 尤度最大化基準による HMM からの音声パラメータ生成法の評価

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2000年春季研究発表会講演論文集   1-7-7   209 - 210   2000

     More details

  • 1.6kbps 低ビットレート符号化方式の検討

    真下哲, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会2000年春季研究発表会講演論文集   2-7-1   241 - 242   2000

     More details

  • Imposture Using Synthetic Speech against Text-prompted Speaker Verification Based on Spectrum and Pitch

    MASUKO Takashi, TOKUDA Keiichi, KOBAYASHI Takao

    IEICE technical report. Speech   SP2000-71 ( 392 )   21 - 26   2000

     More details

    Language:English   Publisher:The Institute of Electronics, Information and Communication Engineers  

    This paper describes security of a text-prompted speaker verification system against imposture using synthetic speech. We construct a text-prompted speaker verification technique in which spectra and pitch are modeled by multi-space probability distribution HMM(MSD-HMM). To model variations of pitch patterns, we take account of contextual factors such as phoneme identity factors or stress-related factors, and apply a decision-tree based context clustering technique. Then, we investigate whether the speaker verification system can reject synthetic speech from the HMM-based speech synthesis system which is trained using speech data from customers of the speaker verification system. Experimental results show that equal error rates for synthetic speech reached over 19% even if the speech synthesis system was trained using only five sentences from each customer, and it is required to develop techniques to discriminate synthetic speech from natural speech.

    CiNii Books

    researchmap

  • A Very Low Bit-Rate Speech Coder Using Mixed Excitation

    HIROYA Sadao, MASHIMO Satoshi, MASUKO Takashi, KOBAYASHI Takao

    IEICE technical report. Speech   SP2000-70 ( 392 )   15 - 20   2000

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    This paper describes a low bit rate speech coder at 1.6 kbps. The proposed coder ueses mixed excitation that is a mixture of periodic pulse and white noise excitation, and mel-generalized cepstral analysis for spectral estimation. An efficient vector qunatization method using statistics of static and dynamic features for speech spectral parameters is also used. To achieve better speech quality, two pitch estimation algorithms, autocorrelation method and instantaneous frequancy method, are applied. The result of subjective evaluation tests shows that the proposed method produces acceptable output speech quality at 1.6kbps.

    CiNii Books

    researchmap

  • スペクトル分析のための尺度を用いたメルケプストラム係数のベクトル量子化

    高橋徹, 徳田恵一, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP2000-67   85 - 90   2000

     More details

  • HMMに基づく音声合成システムの自動構築

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2000年秋季研究発表会講演論文集   1-Q-2   233 - 234   2000

     More details

  • HMM に基づく音声合成システムのためのテキスト解析の検討

    田村正統, 益子貴史, 徳田恵一, 小林隆夫

    日本音響学会2000年春季研究発表会講演論文集   2-P-19   319 - 320   2000

     More details

  • ピクセルベースアプローチによるHMMに基づいた唇動画像生成

    酒向慎司, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会2000年総合大会講演論文集   D-12-64   234   2000

     More details

  • 多空間ガウス混合モデルを用いた話者認識

    服部陽介, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会2000年春季研究発表会講演論文集   3-9-3   99 - 100   2000

     More details

  • Normalized Training for HMM-Based Automatic Lipreading

    南角吉彦, 徳田恵一, 北村正, 小林隆夫

    電子情報通信学会技術研究報告   PRMU99-158   61 - 66   1999

     More details

  • HMMに基づく音声合成のためのスペクトラム, ピッチ, 状態継続長のモデル化

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成11年度春季研究発表会講演論文集   2-3-8   241 - 242   1999

     More details

  • MLLRおよびMAP/VFSを用いたHMM音声合成における話者適応

    田村正統, 益子貴史, 徳田恵一, 小林隆

    日本音響学会平成11年度春季研究発表会講演論文集   2-3-9   243 - 244   1999

     More details

  • MDL基準による音声分析フレーム長と分析次数の同時最適決定

    中西貴裕, 徳田恵一, 小林隆夫, 北村正

    日本音響学会平成11年度春季研究発表会講演論文集   1-3-11   201 - 202   1999

     More details

  • 広帯域音声のMGC-CELP符号化方式における演算量に関する検討

    柳ヶ瀬滋夫, 小石田和人, 徳田恵一, 小林隆夫

    日本音響学会平成11年度春季研究発表会講演論文集   1-3-18   215 - 216   1999

     More details

  • HMMに基づくピッチパターン生成における動的特徴量の効果

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成11年度秋季研究発表会講演論文集   1-3-16   215 - 216   1999

     More details

  • 視覚音声認識のための輝度および位置の正規化学習

    南角吉彦, 徳田恵一, 北村正, 小林隆夫

    電子情報通信学会1999年総合大会講演論文集   D-12-101   274   1999

     More details

  • 固有声(eigenvoice)に基づいた音声合成

    小山晃俊, 徳田恵一, 小林隆夫, 北村正

    日本音響学会平成11年度秋季研究発表会講演論文集   1-3-18   219 - 220   1999

     More details

  • 尤度最大化基準によるHMMからの音声パラメータ生成法の検討

    徳田恵一, 益子貴史, 小林隆夫

    日本音響学会平成11年度秋季研究発表会講演論文集   1-3-15   213 - 214   1999

     More details

  • HMMに基づくテキストからのバイモーダル音声合成に関する検討

    近藤重一, 益子貴史, 徳田恵一, 小林隆夫

    日本音響学会平成11年度春季研究発表会講演論文集   2-P-21   309 - 310   1999

     More details

  • 対数スペクトルの任意基底関数による展開に基づく音声のスペクトル推定

    若子武士, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会論文誌   J82-D-II ( 12 )   2203 - 2211   1999

     More details

  • 合成音声を用いたテキスト指定型話者照合システムにおける詐称の検討

    一ツ松孝文, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会平成11年度春季研究発表会講演論文集   3-3-11   265 - 266   1999

     More details

  • Text-to-Audio-Visual Speech Synthesis Based on Parameter Generation from HMM

    Masatsune Tamura, Shigekazu Kondo, Takashi Masuko, Takao Kobayashi

    Proceedings of 6th European Conference on Speech Communication and Technology   EUROSPEECH'99   959 - 962   1999

     More details

  • On the Security of HMM-Based Speaker Verification Systems Against Imposture Using Synthetic Speech

    Takashi Masuko, Takafumi Hitotsumatsu, Keiichi Tokuda, Takao Kobayashi

    Proceedings of 6th European Conference on Speech Communication and Technology   EUROSPEECH'99   1223 - 1226   1999

     More details

  • Very Low Bit Rate Speech Coding Based on HMMs

    Transactions of the Institue of Electronics, Information and Communication Engineers D-II   J82-D-II ( 11 )   1857 - 1864   1999

     More details

  • Speech Spectral Estimation Based on Expansion of Log Spectrum by Arbitrary Basis Functions

    Transactions of the Institue of Electronics, Information and Communication Engineers D-II   J82-D-II ( 12 )   2203 - 2211   1999

     More details

  • HMMに基づいた唇動画像の生成 - 画像ベースアプローチ -

    広井順, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成11年度春季研究発表会講演論文集   2-P-22   311 - 312   1999

     More details

  • Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis

    Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proceedings of 6th European Conference on Speech Communication and Technology   EUROSPEECH'99   2347 - 2350   1999

     More details

  • Hidden Markov Models Based on Multi-Space Probability Distribution for Pitch Pattern Modeling

    Keiichi Tokuda, Takashi Masuko Noboru, Miyazaki, Takao Kobayashi

    Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing   ICASSP'99   229 - 232   1999

     More details

  • Hidden Markov models based on multi-space probability distribution for pitch pattern modeling

    K Tokuda, T Masuko, N Miyazaki, T Kobayashi

    ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI   ICASSP'99   229 - 232   1999

     More details

    Language:English  

    Web of Science

    researchmap

  • HMMに基づく音声合成におけるスペクトル・ピッチ・状態継続長の同時モデル化

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP99-59   33 - 38   1999

     More details

  • On the Security of HMM-Based Speaker Verification Systems Against Imposture Using Synthetic Speech

    Takashi Masuko, Takafumi Hitotsumatsu, Keiichi Tokuda, Takao Kobayashi

    Proceedings of 6th European Conference on Speech Communication and Technology   EUROSPEECH'99   1223 - 1226   1999

     More details

  • Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis

    Takayoshi Yoshimura Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura

    Proceedings of 6th European Conference on Speech Communication and Technology   EUROSPEECH'99   2347 - 2350   1999

     More details

  • HMM に基づいた極低ビットレート音声符号化

    広井順, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会論文誌   J82-D-II ( 11 )   1857 - 1864   1999

     More details

  • Text-to-Audio-Visual Speech Synthesis Based on Parameter Generation from HMM

    Masatsune Tamura, Shigekazu Kondo, Takashi Masuko, Takao Kobayashi

    Proceedings of 6th European Conference on Speech Communication and Technology   EUROSPEECH'99   959 - 962   1999

     More details

  • 不特定話者HMM認識ボコーダの音質向上に関する検討

    高橋史生, 益子貴史, 徳田恵一, 小林隆夫

    日本音響学会平成11年度春季研究発表会講演論文集   2-P-23   313 - 314   1999

  • HMMに基づく音声合成(招待講演)

    小林隆夫

    日本音響学会平成11年度秋季研究発表会講演論文集   1-3-11   201 - 204   1999

     More details

  • ピクセルベースアプローチによるHMMに基づいた唇動画像の生成

    酒向慎司, 徳田恵一, 北村正, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   PRMU99-157   55 - 60   1999

     More details

  • メル一般化ケプストラム分析に基づくCELP音声符号化

    小石田和人, 徳田恵一, 小林隆夫, 今井聖

    電子情報通信学会論文誌   J81-A ( 2 )   252 - 260   1998

     More details

  • メルケプストラムをパラメータとする音声強調における事前情報の検討

    山内和幸, 益子貴史, 小林隆夫

    日本音響学会平成10年度春季研究発表会講演論文集   3-7-18   289 - 290   1998

     More details

  • 音声分析の統一的手法

    小林隆夫

    Journal of Signal Processing「信号処理」   2 ( 6 )   390 - 397   1998

     More details

  • 2次オールパス関数による周波数変換を利用した音声のメルケプストラム分析

    徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成10年度春季研究発表会講演論文集   3-7-13   279 - 280   1998

     More details

  • 2次オールパス関数による周波数変換を利用したメルケプストラム分析の音声分析合成における評価

    若子武士, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成10年度春季研究発表会講演論文集   3-7-14   281 - 282   1998

     More details

  • HMMに基づくテキストからの音声・唇動画像の同時生成

    増渕淳, 田村正統, 宮川公成, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会平成10年度春季研究発表会講演論文集   2-P-6   305 - 306   1998

     More details

  • HMM音声合成に基づく声質変換における話者適応手法の検討

    田村正統, 益子貴史, 徳田恵一, 小林隆夫

    日本音響学会平成10年度春季研究発表会講演論文集   2-P-13   319 - 320   1998

     More details

  • 多空間出力分布並列HMMによるピッチパタン生成

    加藤寿彦, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会平成10年度春季研究発表会講演論文集   1-7-19   217 - 218   1998

     More details

  • メル一般化ケプストラム分析に基づく広帯域CELPの品質評価

    平林剛, 小石田和人, 徳田恵一, 小林隆夫

    日本音響学会平成10年度春季研究発表会講演論文集   2-7-7   247 - 248   1998

     More details

  • ピッチパタンモデリングのための多空間上の確率分布に基づいたHMM

    宮崎昇, 徳田恵一, 益子貴史, 小林隆夫

    日本音響学会平成10年度春季研究発表会講演論文集   1-7-17   213 - 214   1998

     More details

  • 多空間上の確率分布に基づいたHMMによるピッチパタン生成

    宮崎昇, 徳田恵一, 益子貴史, 小林隆夫

    日本音響学会平成10年度春季研究発表会講演論文集   1-7-18   215 - 216   1998

     More details

  • HMMに基づく話者照合システムにおける合成音声による詐称の検討

    一ツ松孝文, 益子貴史, 小林隆夫, 徳田恵一

    電子情報通信学会技術研究報告   SP98-106   75 - 82   1998

     More details

  • 音声のケプストラム分析,メルケプストラム分析

    小林隆夫

    電子情報通信学会技術研究報告   SP98-56   33 - 40   1998

     More details

  • A Very Low Bit Rate Speech Coder Using HMM-Based Speech Recognition/Synthesis

    Keiichi Tokuda, Takashi Masuko Jun, Hiroi, Takao Kobayashi, Tadashi Kitamura

    Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing   ICASSP'98   609 - 612   1998

  • Text-to-visual speech synthesis based on parameter generation from HMM

    T Masuko, T Kobayashi, M Tamura, J Masubuchi, K Tokuda

    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6   ICASSP'98   3745 - 3748   1998

     More details

    Language:English  

    Web of Science

    researchmap

  • Speaker Adaptation for HMM-based Speech Synthesis System Using MLLR

    Masatsune Tamura, Takashi Masuko Keiichi Tokuda, Takao Kobayashi

    Proceedings of 3rd ESCA/ COSCOSDA International Workshop on Speech Synthesis   273 - 276   1998

     More details

  • A wideband CELP speech coder at 16 kbit/s based on mel-generalized cepstral analysis

    K Koishida, G Hirabayashi, K Tokuda, T Kobayashi

    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6   ICASSP'98   161 - 164   1998

     More details

    Language:English  

    Web of Science

    researchmap

  • A Very Low Bit Rate Speech Coder Using HMM with Speaker Adaptation

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

    Proceedings of 5th International Conference on Spoken Language Processing   ICSLP'98   507 - 510   1998

     More details

  • A 16kbit/s Wideband CELP Coder Using Mel-Generalized Cepstral Analysis and Its Subjective Evaluation

    Kazuhito Koishida Gou Hirabayashi Keiichi Tokuda, Takao Kobayashi

    Proceedings of 5th International Conference on Spoken Language Processing   ICSLP'98   2583 - 2586   1998

     More details

  • Visual Speech Ssynthesis Based on Parameter Generation from HMM: Speech-Driven and Text-and-Speech-Driven Approaches

    Masatsune Tamura, Takashi Masuko, Takao Kobayashi Keiichi Tokuda

    Proceedings of International Conference on Auditory-Visual Speech Processing   AVSP'98   219 - 224   1998

     More details

  • Duration Modeling for HMM-based Speech Synthesis

    Takayoshi Yoshimura Takashi Masuko Keiichi Tokuda Takao Kobayashi, Tadashi Kitamura

    Proceedings of 5th International Conference on Spoken Language Processing   ICSLP'98   29 - 32   1998

     More details

  • HMM認識ボコーダの不特定話者化に関する検討

    益子貴史, 徳田恵一, 小林隆夫

    日本音響学会平成10年度秋季研究発表会講演論文集   3-2-12   271 - 272   1998

     More details

  • HMMに基づく音声合成のための状態継続長モデルの構築

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成10年度秋季研究発表会講演論文集   1-2-8   189 - 190   1998

     More details

  • 音声駆動およびテキスト・音声駆動による唇動画像の生成

    田村正統, 益子貴史, 小林隆夫, 徳田恵一

    日本音響学会平成10年度秋季研究発表会講演論文集   2-P-14   313 - 314   1998

     More details

  • 多空間上の確率分布を用いた HMM によるピッチパタン生成の検討

    宮崎昇, 徳田恵一, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   SP98-12   19 - 26   1998

     More details

  • 2次オールパス関数による周波数変換を利用したメルケプストラム分析の音声認識における評価

    若子武士, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    日本音響学会平成10年度秋季研究発表会講演論文集   1-1-2   3 - 4   1998

     More details

  • テキスト及び音声からの唇動画像の自動生成

    田村正統, 益子貴史, 小林隆夫

    Human Interface News and Report   13 ( 2 )   213 - 218   1998

     More details

  • 多空間上の確率分布に基づいたHMMとピッチパタンモデリングへの応用

    宮崎昇, 徳田恵一, 益子貴史, 小林隆夫

    電子情報通信学会技術研究報告   SP98-11   13 - 18   1998

     More details

  • HMMに基づいた極低ビットレート音声符号化

    広井順, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP98-63   39 - 44   1998

     More details

  • HMMに基づく音声合成のための状態継続長モデルの構築

    吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   45 - 50   1998

     More details

  • 対数スペクトルの任意基底関数による展開に基づいた音声のスペクトル推定とその応用

    若子武士, 徳田恵一, 益子貴史, 小林隆夫, 北村正

    電子情報通信学会技術研究報告   SP98-52   1 - 8   1998

     More details

  • A very low bit rate speech coder using HMM-based speech recognition/synthesis techniques

    Keiichi Tokuda, Takashi Masuko, Jun Hiroi, Takao Kobayashi, Tadashi Kitamura

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   2   609 - 612   1998

     More details

  • Text-to-visual speech synthesis based on parameter generation from HMM

    Takashi Masuko, Takao Kobayashi, Masatsune Tamura, Jun Masubuchi, Keiichi Tokuda

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   6   3745 - 3748   1998

     More details

  • A 16kbit/s Wideband CELP Coder Using Mel-Generalized Cepstral Analysis and Its Subjective Evaluation

    Kazuhito Koishida Gou Hirabayashi Keiichi Tokuda, Takao Kobayashi

    Proceedings of 5th International Conference on Spoken Language Processing   ICSLP'98   2583 - 2586   1998

     More details

  • Speaker Adaptation for HMM-based Speech Synthesis System Using MLLR

    Masatsune Tamura, Takashi Masuko Keiichi Tokuda, Takao Kobayashi

    Proceedings of 3rd ESCA/ COSCOSDA International Workshop on Speech Synthesis   273 - 276   1998

     More details

  • Duration Modeling for HMM-based Speech Synthesis

    Takayoshi Yoshimura Takashi Masuko Keiichi Tokuda Takao Kobayashi, Tadashi Kitamura

    Proceedings of 5th International Conference on Spoken Language Processing   ICSLP'98   29 - 32   1998

     More details

  • A Very Low Bit Rate Speech Coder Using HMM with Speaker Adaptation

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

    Proceedings of 5th International Conference on Spoken Language Processing   ICSLP'98   507 - 510   1998

     More details

  • CELP Speech Coding Based on Mel-Generalized Cepstral Analysis

    Transactions of the Institue of Electronics, Information and Communication Engineers A   J81-A ( 2 )   252 - 260   1998

     More details

  • Visual Speech Ssynthesis Based on Parameter Generation from HMM: Speech-Driven and Text-and-Speech-Driven Approaches

    Masatsune Tamura, Takashi Masuko, Takao Kobayashi Keiichi Tokuda

    Proceedings of International Conference on Auditory-Visual Speech Processing   AVSP'98   219 - 224   1998

     More details

  • 自己組織化Feature Mapに基づいたHMMとその音声認識への応用

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   2-1-14   75 - 76   1997

     More details

  • ML基準パラメータ系列生成に基づく半連続HMMの雑音適応手法の評価

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   2-Q-16   147 - 148   1997

     More details

  • メル一般化ケプストラム分析に基づく広帯域音声のCELP符号化の検討

    小林隆夫

    電子情報通信学会技術研究報告   SP97-41   29 - 36   1997

     More details

  • HMMを用いた音声合成における話者適応による声質変換

    小林隆夫

    日本音響学会平成9年度春季研究発表会講演論文集   3-7-5   267 - 268   1997

     More details

  • HMMを用いた唇動画像の生成

    小林隆夫

    電子情報通信学会技術研究報告   SP97-6   33 - 38   1997

     More details

  • HMMに基づく音声合成システムにおける話者補間

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   1-P-17   337 - 338   1997

     More details

  • 音声パラメータの静的・動的特徴の統計量を用いたベクトル量子化の検討

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   1-2-11   217 - 218   1997

     More details

  • HMMに基づくテキストから唇動画像生成

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   1-P-11   325 - 326   1997

     More details

  • Voice characteristics conversion for HMM-based speech synthesis system

    T Masuko, K Tokuda, T Kobayashi, S Imai

    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V   ICASSP-97 ( 3 )   1611 - 1614   1997

     More details

    Language:English  

    Web of Science

    researchmap

  • Speaker Interpolation in HMM-Based Speech Synthesis System

    Takao Kobayashi

    1-P-17   337 - 338   1997

     More details

  • 対数スペクトルの任意基底関数による展開に基づいた音声のスペクトル推定

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   1-P-22   347 - 348   1997

     More details

  • A Study on Vector Quantization of Speech Spectral Parameters Using Static and Dynamic Features

    Takao Kobayashi

    1-2-11   217 - 218   1997

     More details

  • HMM-Based Lip Movement Synthesis from Text

    Takao Kobayashi

    1-P-11   325 - 326   1997

     More details

  • HMMs Based on Self-Organizing Feature Map and Its Application to Speech Recognition

    Takao Kobayashi

    2-1-14   75 - 76   1997

     More details

  • An Evaluation of Noise Environment Evaluation Method for Semi-Continuous HMM based on ML Parameter Generation

    Takao Kobayashi

    2-Q-16   147 - 148   1997

     More details

  • Speech Synthesis Using HMMs Based on Mel-Cepstral Representaion

    Takao Kobayashi

    Technical Report of IEICE   SP97-41   29 - 36   1997

     More details

  • Voice Characteristics Conversion Using Speaker Adaptation Technipue for HMM-based Speech Synthesis

    Takao Kobayashi

    3-7-5   267 - 268   1997

     More details

  • Speaker Iinterpolation in HMM-Based Speech Synthesis System

    Takao Kobayashi

    Proceedings 5th European Conference on Speech Communication and Technology   EUROSPEECH-97 ( 5 )   2523 - 2526   1997

     More details

  • Lip Movement Synthesis Using HMMs

    Takao Kobayashi

    Technical Report of IEICE   SP97-6   33 - 38   1997

     More details

  • HMM Compensation for Noisy Speech Recognition Based on Cepstral Parameter Generation

    Takao Kobayashi

    Proceedings 5th European Conference on Speech Communication and Technology   EUROSPEECH-97 ( 3 )   1583 - 1586   1997

     More details

  • Vector Quantization of Speech Spectral Parameters Using Statistics of Dynamic Features

    Kazuhito Koishida Keiichi Tokuda, Takashi Masuko, Takao Kobayashi

    Proceedings of International Conference on Speech Processing   ICSP-97   247 - 252   1997

     More details

  • Spectral Quantization Using Statistics of Static and Dynamic Features

    Takao Kobayashi

    1997 IEEE Workshop on Speech Coding for Telecommunications Proceedings   19 - 20   1997

     More details

  • Efficient Encoding of Mel-Generalized Cepstrum for CELP Coders

    Takao Kobayashi

    Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP-97 ( 2 )   1355 - 135   1997

     More details

  • Voice Characteristics Conversion for HMM-based Speech Synthesis System

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

    Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP-97 ( 3 )   1611 - 1614   1997

     More details

  • Spectral Representaion of Speech Based on Mel-Generalized Cepstral Coefficients and Its Properties

    Takao Kobayashi

    Transactions of the Institue of Electronics, Information and Communication Engineers A   J80-A ( 11 )   1999 - 2006   1997

     More details

  • The IF Spectrogram : A New Spectral Representation

    Takao Kobayashi

    Proceedings of International Symposium on Simulation, Visualization and Auralization for Acoustics Research and Education   ASVA-97   423 - 430   1997

     More details

  • Very Low Bit Rate Speech Coding Based on HMMs

    Takao Kobayashi

    1-P-24   351 - 352   1997

     More details

  • An Algorithm for Speech Parameter Generation from HMM Using Dynamic Features

    Takao Kobayashi

    The Journal of the Acoustical Society of Japan   53 ( 3 )   192 - 200   1997

     More details

    Language:Japanese   Publisher:The Acoustical Society of Japan (ASJ)  

    DOI: 10.20697/jasj.53.3_192

    CiNii Books

    researchmap

  • Speech Spectral Estimation Based on Expansion of Log Spectraum by Arbitrary Basis Functions

    Takao Kobayashi

    1-P-22   347 - 348   1997

     More details

  • メル一般化ケプストラム係数に基づく音声のスペクトル表現とその諸特性

    小林隆夫

    電子情報通信学会論文誌   J80-A ( 11 )   1999 - 2006   1997

     More details

  • The IF Spectrogram : A New Spectral Representation

    Takao Kobayashi

    Proceedings of International Symposium on Simulation, Visualization and Auralization for Acoustics Research and Education   ASVA-97   423 - 430   1997

     More details

  • HMMに基づいた極低ビットレート音声符号化

    小林隆夫

    日本音響学会平成9年度秋季研究発表会講演論文集   1-P-24   351 - 352   1997

     More details

  • An algorithm for speech parameter generation from HMM using dynamic features

    TOKUDA Keiichi, MASUKO Takashi, KOBAYASHI Takao, IMAI Satoshi

    The Journal of the Acoustical Society of Japan   53 ( 3 )   192 - 200   1997

     More details

    Language:Japanese   Publisher:The Acoustical Society of Japan (ASJ)  

    DOI: 10.20697/jasj.53.3_192

    CiNii Books

    researchmap

  • HMM Compensation for Noisy Speech Recognition Based on Cepstral Parameter Generation

    Takao Kobayashi

    Proceedings 5th European Conference on Speech Communication and Technology   EUROSPEECH-97 ( 3 )   1583 - 1586   1997

     More details

  • Speaker Iinterpolation in HMM-Based Speech Synthesis System

    Takao Kobayashi

    Proceedings 5th European Conference on Speech Communication and Technology   EUROSPEECH-97 ( 5 )   2523 - 2526   1997

     More details

  • Vector Quantization of Speech Spectral Parameters Using Statistics of Dynamic Features

    Kazuhito Koishida Keiichi Tokuda, Takashi Masuko, Takao Kobayashi

    Proceedings of International Conference on Speech Processing   ICSP-97   247 - 252   1997

     More details

  • Spectral quantization using statistics of static and dynamic features

    K Koishida, K Tokuda, T Masuko, T Kobayashi

    1997 IEEE WORKSHOP ON SPEECH CODING FOR TELECOMMUNICATIONS, PROCEEDINGS   19 - 20   1997

     More details

    Language:English  

    Web of Science

    researchmap

  • Efficient Encoding of Mel-Generalized Cepstrum for CELP Coders

    Takao Kobayashi

    Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP-97 ( 2 )   1355 - 135   1997

     More details

  • Noisy Speech Recognition Using Semi-Continuous HMM Based on ML Parameter Generation

    Takao Kobayashi

    2-Q-13   155 - 156   1996

     More details

  • Speech Coding Based on Mel-Generalized Cepstral Analysis and Its Evaluation

    Takao Kobayashi

    1-4-20   257 - 258   1996

     More details

  • The Amplitude Spectrum of Speech with Respect to Instantaneous Frequency

    Takao Kobayashi

    2-P-19   339 - 340   1996

     More details

  • A Study on Phoneme Models fro Speech Synthesis Using HMMs.

    Takao Kobayashi

    2-4-5   273 - 274   1996

     More details

  • CELP coding system based on mel-generalized cepstral analysis

    K Koishida, K Tokuda, T Kobayashi, S Imai

    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4   ICSLP-96 ( 1 )   318 - 321   1996

     More details

    Language:English  

    Web of Science

    researchmap

  • 動的特徴を用いたHMMに基づく音声合成

    益子貴史, 徳田恵一, 小林隆夫, 今井聖

    電子情報通信学会論文誌   J79-D-II ( 12 )   2184 - 2190   1996

     More details

  • Speech synthesis using HMMS with dynamic features

    T Masuko, K Tokuda, T Kobayashi, S Imai

    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6   ICASSP-96 ( 1 )   389 - 392   1996

     More details

    Language:English  

    Web of Science

    researchmap

  • メルケプストラムをパラメータとするHMMに基づく音声合成

    益子貴史, 徳田恵一, 小林隆夫, 今井聖

    電子情報通信学会技術研究報告   SP95-123   43 - 50   1996

     More details

  • Hybrid Learning for Radial Basis Function Networks

    Takao Kobayashi

    Technical Report of IEICE   NC95-155   9 - 14   1996

     More details

  • Noisy Speech Recognition Using HMM-Based Cepstral Parameter Generation and Compensation

    Takao Kobayashi, Takashi Masuko Keiichi Tokuda, Satoshi Imai

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2790 - 2790   1996

     More details

  • HMMからの音声パラメータ生成アルゴリズム

    小林隆夫

    電子情報通信学会技術研究報告   SP95-122   35 - 42   1996

     More details

  • HMM-Based Speech Synthesis with Various Voice Characteristics

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2756 - 2756   1996

     More details

  • Quantization of Vector Sequences Using Statistics of Neighboring Input Vectors

    Takao Kobayashi

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2762 - 2763   1996

     More details

  • Robust pitch estimation with harmonics enhancement in noisy environments based on instantaneous frequency

    T Abe, T Kobayashi, S Imai

    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4   ICSLP-96 ( 2 )   1277 - 1280   1996

     More details

    Language:English  

    Web of Science

    researchmap

  • Spectral Representation of Speech Using Mel-Generalized Cepstral Coefficients

    Takao Kobayashi

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2760 - 2760   1996

     More details

  • 改良DFT-MUSIC法を用いた低SNR環境における瞬時周波数の推定

    江川護, 小林隆夫, 今井聖

    電子情報通信学会1996年総合大会講演論文集   A-158   160 - 160   1996

     More details

  • HMMを用いた音声合成における音素モデルの検討

    小林隆夫

    日本音響学会平成8年度春季研究発表会講演論文集   2-4-5   273 - 274   1996

     More details

  • HMM-Based Speech Synthesis Using Dynamic Features

    Transactions of the Institute of Electronics, Information and Communication Engineers D-II   J79-D-II ( 12 )   2184 - 2190   1996

     More details

  • Robust Pitch Estimation Based Instantaneous Frequency in Noisy Environment

    Transactions of the Institute of Electronics, Information and Communication Engineers D-II   J79-D-II ( 11 )   1771 - 1781   1996

     More details

  • Quantization of Vector Sequences Using Statistics of Neighboring Input Vectors

    Takao Kobayashi

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2762 - 2763   1996

     More details

  • Noisy Speech Recognition Using HMM-Based Cepstral Parameter Generation and Compensation

    Takao Kobayashi, Takashi Masuko Keiichi Tokuda, Satoshi Imai

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2790 - 2790   1996

     More details

  • Spectral Representation of Speech Using Mel-Generalized Cepstral Coefficients

    Takao Kobayashi

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2760 - 2760   1996

     More details

  • HMM-Based Speech Synthesis with Various Voice Characteristics

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

    Journal of the Acoustical Society of America   100 ( 4-Pt.2 )   2756 - 2756   1996

     More details

  • Speech Synthesis Using HMMs with Dynamic Features

    Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

    Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing   ICASSP-96 ( 1 )   389 - 392   1996

     More details

  • CELP Coding System Based on Mel-Generalized Cepstral Analysis

    Kazuhito Koishida Keiichi Tokuda, Takao Kobayashi, Satoshi Imai

    Proceedings of 4th International Conference on Spoken Language Processing   ICSLP-96 ( 1 )   318 - 321   1996

     More details

  • Hybrid Learning for Radial Basis Function Networks

    Takao Kobayashi

    Technical Report of IEICE   NC95-155   9 - 14   1996

     More details

  • Instantaneous Frequency Estimation in Low SNR Environments Using Improved DFT-MUSIC

    A-158   160 - 160   1996

     More details

  • A Speech Parameter Generation Algorithm Based on HMM

    Takao Kobayashi

    SP95-122   35 - 42   1996

     More details

  • Speech Synthesis Using HMMs Based on Mel-Cepstral Representaion

    SP95-123   43 - 50   1996

     More details

  • Noisy Environment Adaptation of HMM Using ML Parameter Generation

    Takao Kobayashi

    2-Q-12   153 - 154   1996

     More details

  • ML基準パラメータ系列生成に基づく半連続HMMによる雑音音声認識

    小林隆夫

    日本音響学会平成8年度秋季研究発表会講演論文集   2-Q-13   155 - 156   1996

     More details

  • MA予測を用いたメル一般化ケプストラムの量子化

    小林隆夫

    日本音響学会平成8年度秋季研究発表会講演論文集   3-4-1   261 - 262   1996

     More details

  • 音声信号の瞬時周波数に基づく振幅スペクトル表現

    小林隆夫

    日本音響学会平成8年度春季研究発表会講演論文集   2-P-19   339 - 340   1996

     More details

  • ML基準パラメータ系列生成に基づくHMMの雑音環境への適応

    小林隆夫

    日本音響学会平成8年度秋季研究発表会講演論文集   2-Q-12   153 - 154   1996

     More details

  • メル一般化ケプストラムに基づくCELP符号化系とその評価

    小林隆夫

    日本音響学会平成8年度春季研究発表会講演論文集   1-4-20   257 - 258   1996

     More details

  • Quantization of Mel-Cepstrum Using MA Prediction

    Takao Kobayashi

    3-4-1   261 - 262   1996

     More details

  • 瞬時周波数に基づく雑音環境下でのピッチ推定

    阿部敏彦, 小林隆夫, 今井聖

    電子情報通信学会論文誌   J79-D-II ( 11 )   1771 - 1781   1996

     More details

  • ADAPTIVE CEPSTRAL ANALYSIS OF SPEECH

    K TOKUDA, T KOBAYASHI, S IMAI

    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING   3 ( 6 )   481 - 489   1995.11

     More details

  • HARMONICS ESTIMATION BASED ON INSTANTANEOUS FREQUENCY AND ITS APPLICATION TO PITCH DETERMINATION OF SPEECH

    T ABE, T KOBAYASHI, S IMAI

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E78D ( 9 )   1188 - 1194   1995.9

     More details

    Language:English  

    Web of Science

    researchmap

  • Spectral Representation of Speech Using Mel-Generalized Cepstrum and Its Properties

    Takao Kobayashi

    Technical report of IEICE. DSP   SP95-49 ( 226 )   1 - 8   1995

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    The mel-generalized cepstral analysis method includes the several speech analysis method and it was shown that this method was useful for speech processing. In this paper, we discuss the spectral representation of speech using mel-generalized cepstral coefficients for speech-coding and speech-synthesis applications. The stability of the synthesis filter can be easily ensured even if the proposed spectral parameter is quantized. First, the statistical distribution and computational complexity for calculating the parameter from mel-generalized cepstral coefficients are investigated using speech database. Next, the quantization and interpolation properties of the proposed parameter are compared with that of LSP. As a result, it is shown that proposed parameter has better performance than LSP.

    CiNii Books

    researchmap

  • メル一般化ケプストラムパラメータの音素認識における評価

    小林隆夫

    日本音響学会平成7年度春季研究発表会講演論文集   1-Q-1   97 - 98   1995

     More details

  • 瞬時周波数に基づく雑音環境下でのピッチ推定

    小林隆夫

    電子情報通信学会技術研究報告書   SP95-79   47 - 54   1995

     More details

  • 雑音環境下での瞬時周波数推定

    小林隆夫

    電子情報通信学会技術研究報告書   DSP95-131   13 - 18   1995

     More details

  • メル一般化ケプストラムをパラメータによる音声のスペクトル表現とその諸特性

    小林隆夫

    電子情報通信学会技術研究報告書   SP95-49   1 - 8   1995

     More details

  • メル一般化ケプストラム分析に基づくCELP符号化

    小林隆夫

    電子情報通信学会技術研究報告書   SP95-51   17 - 24   1995

     More details

  • an Algorithm for Speech Parameter Generation form Continuous Mixture HMM With Dynamic Features

    Takao Kobayashi

    Proceedings of 4th European Conference on Speech Communication and Technology   EUROSPEECH-95   757 - 760   1995

     More details

  • 時間軸伸縮を導入した瞬時周波数に基づく倍音推定

    小林隆夫

    電子情報通信学会技術研究報告書   SP94-94   23 - 28   1995

     More details

  • SPEECH PARAMETER GENERATION FROM HMM USING DYNAMIC FEATURES

    K TOKUDA, T KOBAYASHI, S IMAI

    1995 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING - CONFERENCE PROCEEDINGS, VOLS 1-5   ICASSP-95 ( 1 )   660 - 663   1995

     More details

    Language:English  

    Web of Science

    researchmap

  • Harmonic Tracking and Pitch Extraction Based on Instantaneous Frequency

    Takao Kobayashi

    Proceedings of 1995 International Conference on Acoustics, Speech and Signal Processing   ICASSP-95 ( 1 )   756 - 59   1995

     More details

  • CELP CODING BASED ON MEL-CEPSTRAL ANALYSIS

    K KOISHIDA, K TOKUDA, T KOBAYASHI, S IMAI

    1995 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING - CONFERENCE PROCEEDINGS, VOLS 1-5   ICASSP-95 ( 1 )   33 - 36   1995

     More details

    Language:English  

    Web of Science

    researchmap

  • HMMを用いた音声合成法に関する検討

    小林隆夫

    日本音響学会平成7年度秋季研究発表会講演論文集   2-1-5   253 - 254   1995

     More details

  • メル一般化ケプストラム分析に基づく音声符号化の検討

    小林隆夫

    日本音響学会平成7年度秋季研究発表会講演論文集   3-1-11   289 - 290   1995

     More details

  • 低ビット音声符号化のためのメルケプストラム係数のベクトル量子化

    小林隆夫

    日本音響学会平成7年度春季研究発表会講演論文集   1-4-10   237 - 238   1995

     More details

  • 音声信号の非線形伸縮と瞬時周波数に基づく倍音推定

    小林隆夫

    日本音響学会平成7年度春季研究発表会講演論文集   1-4-21   259 - 260   1995

     More details

  • Speech Parameter Generation form HMM using Dynamic Features

    Takao Kobayashi

    Proceedings of 1995 International Conference on Acoustics, Speech and Signal Processing   ICASSP-95 ( 1 )   660 - 663   1995

     More details

  • Harmonic Tracking and Pitch Extraction Based on Instantaneous Frequency

    Takao Kobayashi

    Proceedings of 1995 International Conference on Acoustics, Speech and Signal Processing   ICASSP-95 ( 1 )   756 - 59   1995

     More details

  • an Algorithm for Speech Parameter Generation form Continuous Mixture HMM With Dynamic Features

    Takao Kobayashi

    Proceedings of 4th European Conference on Speech Communication and Technology   EUROSPEECH-95   757 - 760   1995

     More details

  • A Study on the Speech Synthesis Method Using Hmms

    Takao Kobayashi

    2-1-5   253 - 254   1995

     More details

  • Speech Coding Based on Mel-Generalized Cepstrul

    Takao Kobayashi

    3-1-11   289 - 290   1995

     More details

  • Vector Quantization of Mel-Cepstrum for Low Bit Rate Speech Coding

    Takao Kobayashi

    1-4-10   237 - 238   1995

     More details

  • Harmonic Analysis Based on nonlinear Time-Warping and Instantaneous Frequency

    Takao Kobayashi

    1-4-21   259 - 260   1995

     More details

  • Instantaneous Frequency Estimation in low SNR Environments

    Takao Kobayashi

    Technical report of IEICE. DSP   DSP95-131 ( 417 )   13 - 18   1995

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    The MUSIC Method is a member of the eigendecomposition-based spectral estimators and because of its high resolution capability, it is widely studied for direction and frequency estimation. In this report, the MUSIC method is applied to the instantaneous frequency estimation for nonstationaly signal, and we propose an improved method for lower SNR signal by the robust estimation of eigenvector in noise and prefilter using estimated eigenvectors. It is shown that the proposed method has about 6dB lower SNR threshold and superior performance in comparison with the other IF estimators such is Wigner distribution.

    CiNii Books

    researchmap

  • On the Use of Mel-Generalized Cepstral Parameter in Phoneme Recognition

    Takao Kobayashi

    1-Q-1   97 - 98   1995

     More details

  • CELP Coder Based on Mel-Generalized Cepstral Analysis

    Takao Kobayashi

    Technical report of IEICE. DSP   SP95-51 ( 226 )   17 - 24   1995

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    It is expected that the mel-generalized cepstrum is useful for speech coding since the speech spectrum can be represented efficiently by utilizing the mel-generalized cepstrum. To show this we propose the CELP coder based on mel-generalized cepstral analysis. In the coder the perceptual weighting and postfiltering are carried out through the mel-generalized cepstral coefficients. It is shown that the objective speech quality of proposed coder is slightly higher than that of conventional CELP.

    CiNii Books

    researchmap

  • Pitch Estimation Based on Instantaneous Frequency in Noisy Environments

    Takao Kobayashi

    SP95-79   47 - 54   1995

     More details

  • Time-Warping Approach into Harmonics Estimation Based on Instantaneous Frequency

    Takao Kobayashi

    SP94-94   23 - 28   1995

     More details

  • Speech Coding Based on Adaptive Mel-Cepstral Analysis

    Takao Kobayashi

    Proceedings of 1994 International Conference on Acoustics, Speech & Signal Processing   I-197-I-200   1994

     More details

  • 適応メルケプストラム分析を利用した音声符号化とその評価

    小林隆夫

    電子情報通信学会論文誌A   J77-A ( 11 )   1443 - 1452   1994

     More details

  • Mel-Generalized Cepstral Analysis-A Unified Approach to Speech Spectral Estimation

    Takao Kobayashi

    Proceedings of 1994 International Conference on Spoken Language Processing   1043 - 1046   1994

     More details

  • Speech Coding Based on Adaptive Mel-Cepstral Analysis for Noisy Channels

    Takao Kobayashi

    Proceedings of 1994 International Conference on Spoken Language Processing   2087 - 2090   1994

     More details

  • Speech Coding Based on Adaptive Mel-Cepstral Analysis

    Takao Kobayashi

    Proceedings of 1994 International Conference on Acoustics, Speech & Signal Processing   I-197-I-200   1994

     More details

  • Speech Coding Based on Adaptive Mel-Cepstral Analysis and Its Evaluation

    Takao Kobayashi

    Transaction of the Institute of Electronics, Information and Communication Engineers A   J77-A ( 11 )   1443 - 1452   1994

     More details

  • 雑音劣化音声の一般化ケプストラムモデル化における事前情報の利用

    小林隆夫

    電子情報通信学会論文誌A   J77-A ( 7 )   945 - 953   1994

     More details

  • Mel-Generalized Cepstral Analysis-A Unified Approach to Speech Spectral Estimation

    Takao Kobayashi

    Proceedings of 1994 International Conference on Spoken Language Processing   1043 - 1046   1994

     More details

  • Speech Coding Based on Adaptive Mel-Cepstral Analysis for Noisy Channels

    Takao Kobayashi

    Proceedings of 1994 International Conference on Spoken Language Processing   2087 - 2090   1994

     More details

  • On the Use of a priori Information in Generalized Cepstral Modeling of Degraded Speech

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers A   J77-A ( 7 )   945 - 953   1994

     More details

  • Generalized Cepstral Modeling of Degraded Speech and Its Application to Speech Enhancement

    Takao Kobayashi

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   E76-A ( 8 )   1300 - 1307   1993

     More details

  • Generalized Cepstral Modeling of Speech Degraded by Additive Noise

    Takao Kobayashi

    Proceedings of European Conterence on Speech Communication and Technology   ( 93 )   609 - 612   1993

     More details

  • Generalized Cepstral Modeling of Speech Degraded by Additive Noise

    Takao Kobayashi

    Proceedings of European Conterence on Speech Communication and Technology   ( 93 )   609 - 612   1993

     More details

  • Generalized Cepstral Modeling of Degraded Speech and Its Application to Speech Enhancement

    Takao Kobayashi

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   E76-A ( 8 )   1300 - 1307   1993

     More details

  • メル一般化ケプストラム分析による音声のスペクトル推定

    小林隆夫

    電子情報通信学会論文誌   J75-A ( 7 )   1124 - 1134   1992

     More details

  • 2-D LMA Filters-Design of Stable Two-Dimensional Digital Filters with Arbitrary Magnitude Function

    Takao Kobayashi

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   E75-A ( 2 )   240 - 246   1992

     More details

  • 2-D LMA Filters-Design of Stable Two-Dimensional Digital Filters with Arbitrary Magnitude Function

    Takao Kobayashi

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   E75-A ( 2 )   240 - 246   1992

     More details

  • Spectral Estimation of Speech by Mel-Generalized Cepstral Analysis

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers   J75-A ( 7 )   1124 - 1134   1992

     More details

  • Spectral Estimation of Speech Based on Mel-Cepstral Representation

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers   J74-A ( 8 )   1240 - 1248   1991

     More details

    Language:Japanese   Publisher:Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1476/00004099/

  • メルケプストラムをパラメータとする音声のスペクトル推定

    小林隆夫

    電子情報通信学会論文誌   J74-A ( 8 )   1240 - 1248   1991

     More details

  • DESIGN OF IIR DIGITAL-FILTERS WITH ARBITRARY LOG MAGNITUDE FUNCTION BY WLS TECHNIQUES

    T KOBAYASHI, S IMAI

    IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING   38 ( 2 )   247 - 252   1990.2

     More details

  • Adaptive Cepstral Analysis-Adaptive Filtering Based on Cepstral Representation

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers   J73-A ( 7 )   1207 - 1215   1990

     More details

    Language:Japanese   Publisher:Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1476/00004037/

  • 適応ケプストラム分析-ケプストラムを係数とする適応フィルター

    小林隆夫

    電子情報通信学会論文誌   J73-A ( 7 )   1207 - 1215   1990

     More details

  • Complex Chebyshev Approximation for IIR Digital Filters with Arbitrary Log Magnitude and Phase Functions

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers   J72-A ( 11 )   1772 - 1778   1989

     More details

  • IIRディジタルフィルタの対数振幅・位相特性の複素チェビシェフ近似

    小林隆夫

    電子情報通信学会論文誌   J72-A ( 11 )   1772 - 1778   1989

     More details

  • 一般化ケプストラムをパラメータとする音声のスペクトル推定

    小林隆夫

    電子情報通信学会論文誌   J72-A ( 3 )   457 - 465   1989

     More details

  • Spectral Estimation of Speech Based on Generalized Cepstral Representation

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers   J72-A ( 3 )   457 - 465   1989

     More details

    Language:Japanese   Publisher:Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1476/00003977/

  • 単語音声認識における一般化ケプストラム距離尺度の検討

    小林隆夫

    電子情報通信学会論文誌   J71-A ( 3 )   608 - 615   1988

     More details

  • On the Use of Generalized Cepstral Distance Measure in Isolated Word Recognition

    Takao Kobayashi

    Transactions of the Institute of Electronics, Information and Communication Engineers   J71-A ( 3 )   608 - 615   1988

     More details

  • 一般化ケプストラム距離尺度

    小林隆夫

    電子通信学会論文誌   J69-A ( 11 )   1431 - 1438   1986

     More details

  • Generalized Cepstral Distance Measures

    Takao Kobayashi

    Transactions of the Institute of Electronics and Communications Engineers of Japan   J69-A ( 11 )   1431 - 1438   1986

     More details

  • SPECTRAL-ANALYSIS USING GENERALIZED CEPSTRUM

    T KOBAYASHI, S IMAI

    IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING   32 ( 5 )   1087 - 1089   1984

     More details

    Language:English   Publishing type:Rapid communication, short report, research note, etc. (scientific journal)  

    DOI: 10.1109/TASSP.1984.1164416

    Web of Science

    PubMed

    researchmap

▼display all

Presentations

  • A study on voice conversion based on F0 quantization and non-parallel training

    2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • HMM-based speech synthesis using quantized-F0-based prosodic context

    2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • HMM-based speaker characteristics emphasis using average voice model

    INTERSPEECH 2009  2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Speaking style adaptation for spontaneous speech recognition using multiple-regression HMM

    INTERSPEECH 2009  2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Emotional speech recognition based on style estimation and adaptationwith multiple-regression HMM

    ICASSP 2009  2009 

     More details

  • A study on discrimination between speech, music, and mixed sounds for broadcast audio signals

    2009 IEICE General Conference  2009 

     More details

  • Perfomance evaluation of acoustic model training technique for speech recognition using style estimation

    ASJ 2009 Spring Meeting  2009 

     More details

  • A study on conversational speech synthesis based on average voice model

    IEICE Technical Report  2010 

     More details

  • Performance evaluation of voice conversion based on F0 quantization and non-parallel training

    IEICE Technical Report  2010 

     More details

  • HMMに基づく対話音声合成のための発話単位の検討

    日本音響学会2010年春季研究発表会  2010 

     More details

  • 平均声に基づく対話音声合成に関する検討

    電子情報通信学会技術研究報告  2010 

     More details

  • F0量子化と非パラレル学習に基づく声質変換の評価

    電子情報通信学会技術研究報告  2010 

     More details

  • HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model

    ICASSP 2010  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Performance evaluation of HMM-based speech synthesis using quantized F0 context

    ASJ 2010 Spring Meeting  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Performance evaluation of HMM-based speech synthesis using quantized F0 context

    ASJ 2010 Spring Meeting  2010 

     More details

  • HMM-based voice conversion from arbitrary speakers using quantized F0 context

    ASJ 2010 Spring Meeting  2010 

     More details

  • A study on utterance unit for HMM-based conversational speech synthesis

    ASJ 2010 Spring Meeting  2010 

     More details

  • 量子化F0韻律コンテキストを用いたHMM音声合成の評価

    日本音響学会2010年春季研究発表会  2010 

     More details

  • 量子化F0コンテキストを用いたHMMに基づく不特定話者声質変換の検討

    日本音響学会2010年春季研究発表会  2010 

     More details

  • 重回帰HSMMを用いた音声のスタイル制御法の検討

    日本音響学会2005年秋季研究発表会講演論文集  2005 

     More details

  • A study on HSMM-based MLLR adaptation

    2004 

     More details

  • MSD-HMMに基づく音声のスタイル識別

    電子情報通信学会技術研究報告  2005 

     More details

  • Human walking motion synthesis based on multiple regression hidden semi-Markov model

    Second International Workshop on Language Understanding and Agents for Real World Interaction, LUAR 2005  2005 

     More details

  • MSD-HMMを用いた音声のスタイル識別の検討

    日本音響学会2005年秋季研究発表会  2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 平均声に基づく音声合成のための話者適応アルゴリズムの検討

    日本音響学会2005年秋季研究発表会  2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 多様な音声合成のためのスタイル適応アルゴリズムの比較検討

    日本音響学会2005年秋季研究発表会  2005 

     More details

  • HMM音声合成におけるESATアルゴリズムの評価

    日本音響学会2005年秋季研究発表会  2005 

     More details

  • Naive Markov Modelによるポーズ予測アルゴリズム

    日本音響学会2005年秋季研究発表会  2005 

     More details

  • 多様な話者性および発話スタイル・感情表現による音声合成

    日本音響学会2005年秋季研究発表会  2005 

     More details

  • アンサンブル学習に基づく音韻継続長のモデル化

    電子情報通信学会・日本音響学会 音声研究会  2005 

     More details

  • 隠れセミマルコフモデルに基づく最尤線形回帰の検討

    2004 

     More details

  • A comparative study of speaker adaptation algorithms for average-voice-based speech synthesis

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A comparative study of style adaptation algorithms for expressive speech synthesis

    2005 

     More details

  • Performance evaluation of ESAT algorithm for HMM-based speech synthesis

    2005 

     More details

  • Pause prediction algorithm based on naive Markov model, by YAMAGISHI

    2005 

     More details

  • A study on style control technique for speech synthesis using multiple regression HSMM

    Proc. the 2005 Autumn Meeting of the Acoustical Society of Japan  2005 

     More details

  • Speech synthesis with diverse speakers' voices, speaking styles, and emotional expressions

    2005 

     More details

  • Phone duration modeling based on ensemble learning

    Technical Report of IEICE  2005 

     More details

  • Model adaptation and adaptive training algorithms for speech synthesis with diverse speaker characteristics

    Technical Report of IEICE  2005 

     More details

  • Performance evaluation of style adaptation for hiden semi-Markov model based speech synthesis

    Technical Report of IEICE  2005 

     More details

  • Generation of walking movements with an arbitrarily prescribed pace

    2005 

     More details

  • A spoken dialogue agent system accepting vague representations

    2005 

     More details

  • 多様な音声合成のためのモデル適応・適応学習アルゴリズムの検討

    電子情報通信学会技術研究報告  2005 

     More details

  • 隠れセミマルコフモデルに基づく音声合成システムのためのスタイル適応手法の評価

    電子情報通信学会技術研究報告  2005 

     More details

  • 歩行速度とテンポを考慮した歩行動作の生成

    電子情報通信学会2005年総合大会  2005 

     More details

  • あいまい表現入力が可能な音声対話エージェントシステムの検討

    電子情報通信学会2005年総合大会  2005 

     More details

  • HMM音声合成における決定木の分割停止基準の検討

    日本音響学会2005年春季研究発表会  2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • モデル補間による発話スタイル・感情表現の制御の検討

    日本音響学会2005年春季研究発表会  2005 

     More details

  • 隠れセミマルコフモデルに基づく適応学習アルゴリズム

    日本音響学会2005年春季研究発表会  2005 

     More details

  • HMM音声合成におけるESATアルゴリズムを用いたモデル適応および適応学習の検討

    日本音響学会2005年春季研究発表会  2005 

     More details

  • Style classification of speech based on MSD-HMM

    IEICE Technical Report  2005 

     More details

  • Human walking motion synthesis based on multiple regression hidden semi-Markov model

    Second International Workshop on Language Understanding and Agents for Real World Interaction, LUAR 2005  2005 

     More details

  • A study on style classification of read speech based on MSD-HMM

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 重回帰HSMMに基づく音声の発話様式・感情表現の推定

    日本音響学会2006年春季研究発表会講演論文集  2006 

     More details

  • 重回帰HSMMに基づく合成音声の声質制御の検討

    日本音響学会2006年春季研究発表会講演論文集  2006 

     More details

  • HSMM音声合成における話者適応とMAPに基づく音響モデル学習法

    日本音響学会2006年春季研究発表会講演論文集  2006 

     More details

  • HMM音声合成のための話者正規化クラスタリングと話者正規化学習

    日本音響学会2006年春季研究発表会講演論文集  2006 

     More details

  • 平均声に基づく音声合成のための話者適応アルゴリズムの評価

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • F0量子化を用いたMSD-HMMに基づく声質変換

    日本音響学会2009年春季研究発表会  2009 

     More details

  • 平均声モデルを用いる合成音声の話者性とスタイルの同時多様化の検討

    電子情報通信学会技術研究報告  2007 

     More details

  • 重回帰HSMMに基づく合成音声のスタイル制御のための平均声からの話者適応手法

    電子情報通信学会技術研究報告  2007 

     More details

  • HMM音声合成におけるスペクトル正規化に基づく音響モデル学習法の検討

    日本音響学会2007年秋季研究発表会  2007 

     More details

  • 合成音声のスタイル制御における平均声からの話者適応手法の検討

    日本音響学会2007年秋季研究発表会  2007 

     More details

  • 多様なスタイル音声合成のための話者・スタイル適応の性能評価

    日本音響学会2007年秋季研究発表会  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Style estimation of speech based on multiple regression hidden semi-Markov model

    INTERSPEECH 2007  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Acoustic model training based on speaker adaptation and MAP modification for HSMM-based speech synthesis

    Proc. the 2006 Spring Meeting of the Acoustical Society of Japan  2006 

     More details

  • Speaker normalization clustering and training for HMM-based speech synthesis

    Proc. the 2006 Spring Meeting of the Acoustical Society of Japan  2006 

     More details

  • Performance evaluation of speaker adaptation algorithms for average-voice-based speech synthesis

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A style control technique for speech synthesis using multiple regression HSMM

    IEICE Technical Report  2006 

     More details

  • A technique for controlling voice quality of synthetic speech using multiple regression HSMM

    Proc. 9th International Conference on Spoken Language Processing  2006 

     More details

  • A study on speaker adaptation for style control of synthetic speech

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A study on style diversity in style control technique for speech synthesis using multiple regression HSMM

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Evaluation of acoustic model training based on combined linear transformation and MAP method

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Performance evaluation of style classification of read speech based on MSD-HMM

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Estimation of speaking style and emotional expression of speech based on multiple regression HSMM

    Proc. the 2006 Spring Meeting of the Acoustical Society of Japan  2006 

     More details

  • A study on a technique for controlling voice quality of synthetic speech using multiple regression HSMM

    Proc. the 2006 Spring Meeting of the Acoustical Society of Japan  2006 

     More details

  • 重回帰HSMMを用いた合成音声のスタイル制御

    電子情報通信学会技術研究報告  2006 

     More details

  • Acoustic model training based on linear transformation and MAP modification for average-voice-based speech synthesis

    IEICE Technical Report  2006 

     More details

  • A style control technique for speech synthesis using multiple regression HSMM

    Proc. 9th International Conference on Spoken Language Processing  2006 

     More details

  • Design of tree-based context clustering for an HMM-based Thai speech synthesis system

    Sixth ISCA Tutorial and Research Workshop on Speech Synthesis, SSW6  2007 

     More details

  • A study on modeling technique for vague expressions of human motion in spoken dialogue agents

    IEICE Technical Report  2007 

     More details

  • A speaker adaptation technique for MRHSMM-based style control of synthetic speech

    ICASSP 2007  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A human motion modeling technique for spoken dialogue agents accepting vague expressions

    2007 IEICE General Conference  2007 

     More details

  • A speaker adaptation technique using average voice model for MRHSMM-based style control of synthetic speech

    IEICE Technical Report  2007 

     More details

  • A study on model training technique using spectral normalization for HMM-based speech synthesis

    ASJ 2007 Spring Meeting  2007 

     More details

  • A speaker adaptation technique for MRHSMM-based style control of synthetic speech

    ASJ 2007 Spring Meeting  2007 

     More details

  • Performance evaluation of speaker and style adaptation technique for speech synthesis with various styles

    ASJ 2007 Autumn Meeting  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Style estimation of speech based on multiple regression hidden semi-Markov model

    INTERSPEECH 2007  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV

    Sixth ISCA Tutorial and Research Workshop on Speech Synthesis, SSW6  2007 

     More details

  • 合成音声のスタイル制御における話者適応の評価

    日本音響学会2007年春季研究発表会  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 重回帰HSMMに基づくスタイル推定とスタイル音声合成の検討

    日本音響学会2007年春季研究発表会  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 平均声と話者・スタイル適応を用いたスタイル制御法の検討

    日本音響学会2007年春季研究発表会  2007 

     More details

  • 平均声に基づく音声合成における合成音声の品質評価

    日本音響学会2007年春季研究発表会  2007 

     More details

  • Speech synthesis with diverse voices and styles using average voice model

    IEICE Technical Report  2007 

     More details

  • Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV

    Sixth ISCA Tutorial and Research Workshop on Speech Synthesis, SSW6  2007 

     More details

  • Design of tree-based context clustering for an HMM-based Thai speech synthesis system

    Sixth ISCA Tutorial and Research Workshop on Speech Synthesis, SSW6  2007 

     More details

  • 対話エージェントにおける不明確性を含む動作表現のモデル化の検討

    電子情報通信学会技術研究報告  2007 

     More details

  • A speaker adaptation technique for MRHSMM-based style control of synthetic speech

    ICASSP 2007  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 不明確性を含む動作表現のためのモデル構築法の検討

    電子情報通信学会2007年総合大会  2007 

     More details

  • Acoustic model training technique for speech recognition using style estimation with multiple-regression HMM

    IEICE Technical Report  2008 

     More details

  • An on-line adaptation technique for emotional speech recognition using style estimation with multiple-regression HMM

    INTERSPEECH 2008  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • スタイル推定に基づく音響モデルのオンライン適応手法

    電子情報通信学会技術研究報告  2008 

     More details

  • Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis

    ICASSP 2008  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A context clustering technique for improvement of tone intelligibility of average-voice-based Thai speech synthesis

    Asian Workshop on Speech Science and Technology  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • CSMAPLRに基づく話者適応におけるハイパーパラメータ選択に関する検討

    日本音響学会2008年春季研究発表会  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • モデル適応に基づく重回帰HSMMによるスタイル推定の検討

    日本音響学会2008年春季研究発表会  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 平均声と話者・スタイル適応に基づく合成音声のスタイル制御の検討

    日本音響学会2008年春季研究発表会  2008 

     More details

  • 平均声方式に基づく音声合成における決定木構築手法の評価

    日本音響学会2008年春季研究発表会  2008 

     More details

  • Blizzard Challenge 2007のための平均声に基づくHMM音声合成システムの評価

    日本音響学会2008年春季研究発表会  2008 

     More details

  • An estimation technique of style expressiveness for emotional speech using model adaptation based on multiple-regression HSMM

    INTERSPEECH 2008  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 平均声からの話者適応手法と重回帰HSMMによる合成音声の声質制御の検討

    日本音響学会2008年秋季研究発表会  2008 

     More details

  • スタイル推定に基づく音響モデルのオンライン適応手法の評価

    日本音響学会2008年秋季研究発表会  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 平均声からの話者適応手法を用いた重回帰HSMMに基づく合成音声の声質制御

    電子情報通信学会技術研究報告  2008 

     More details

  • A speaker adaptation technique for MRHSMM-based style control of synthetic speech

    ASJ 2007 Spring Meeting  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Style estimation and synthesis of speech based on multiple regression HSMM

    ASJ 2007 Spring Meeting  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A study on style control technique for average-voice-based speech synthesis using speaker and style adap-

    ASJ 2007 Spring Meeting  2007 

     More details

  • Objective evaluation of synthesized speech in average-voice-based speech synthesis

    ASJ 2007 Spring Meeting  2007 

     More details

  • 重回帰HMMに基づくスタイル推定を用いた音声認識における音響モデル学習法

    電子情報通信学会技術研究報告  2008 

     More details

  • An on-line adaptation technique for emotional speech recognition using style estimation with multiple-regression HMM

    INTERSPEECH 2008  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • An estimation technique of style expressiveness for emotional speech using model adaptation based on multiple-regression HSMM

    INTERSPEECH 2008  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • F0量子化と非パラレル学習に基づく声質変換の検討

    2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • F0量子化に基づく韻律コンテキストを用いたHMM音声合成

    2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • F0量子化と非パラレル学習に基づく声質変換

    日本音響学会2009年秋季研究発表会講演論文集  2009 

     More details

  • HMM音声合成におけるF0モデルの教師なし学習の検討

    日本音響学会2009年秋季研究発表会講演論文集  2009 

     More details

  • HMMに基づく対話音声合成の検討

    日本音響学会2009年秋季研究発表会講演論文集  2009 

     More details

  • HMM-based speaker characteristics emphasis using average voice model

    INTERSPEECH 2009  2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Speaking style adaptation for spontaneous speech recognition using multiple-regression HMM

    INTERSPEECH 2009  2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 重回帰HMMに基づく自然発話音声の発話様式識別

    電子情報通信学会技術研究報告  2009 

     More details

  • Emotional speech recognition based on style estimation and adaptationwith multiple-regression HMM

    ICASSP 2009  2009 

     More details

  • テレビ放送音に対する音声と音楽およびその混合音の識別に関する検討

    電子情報通信学会2009年総合大会  2009 

     More details

  • スタイル推定を用いた音声認識における音響モデル学習法の評価

    日本音響学会2009年春季研究発表会  2009 

     More details

  • A speaker and style adaptation using average voice model for style control of synthetic speech

    ASJ 2008 Spring Meeting  2008 

     More details

  • A technique for controlling voice quality of synthetic speech using speaker adaptation from average voice model and multiple regression HSMM

    ASJ 2008 Spring Meeting  2008 

     More details

  • Performance evaluation of on-line acoustic model adaptation technique based on style estimation

    ASJ 2008 Spring Meeting  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • An MRHSMM-based voice quality control technique for synthetic speech using speaker adaptation from average voice model

    IEICE Technical Report  2008 

     More details

  • An on-line acoustic model adaptation technique based on style estimation

    IEICE Technical Report  2008 

     More details

  • Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis

    ICASSP 2008  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A context clustering technique for improvement of tone intelligibility of average-voice-based Thai speech synthesis

    Asian Workshop on Speech Science and Technology  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A study on choice of hyperparameter in speaker adaptation for speech synthesis

    ASJ 2008 Spring Meeting  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Style estimation of speech based on multiple regression HSMM using model adaptation

    ASJ 2008 Spring Meeting  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Evaluation of tree-based context clustering techniques for average-voice-based speech synthesis

    ASJ 2008 Spring Meeting  2008 

     More details

  • Performance evaluation of average-voice based speech synthesis system for Blizzard Challenge 2007

    ASJ 2008 Spring Meeting  2008 

     More details

  • Speaking style classification of spontaneous speech based on style estimation

    ASJ 2009 Spring Meeting  2009 

     More details

  • Speech synthesis with diverse styles and voice qualities using average voice model and multiple-regression HSMM

    ASJ 2009 Spring Meeting  2009 

     More details

  • A study on a technique for emphasizing speaker characteristics of synthetic speech based on average voice model

    ASJ 2009 Spring Meeting  2009 

     More details

  • Voice conversion based on MSD-HMM with F0 quantization

    ASJ 2009 Spring Meeting  2009 

     More details

  • HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model

    ICASSP 2010  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • HMM音声合成における韻律コンテキストの評価

    日本音響学会2010年春季研究発表会  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • スタイル推定を用いた自然発話音声の発話様式識別に関する検討

    日本音響学会2009年春季研究発表会  2009 

     More details

  • 平均声と重回帰HSMM を用いた合成音声の多様なスタイル・声質制御の検討

    日本音響学会2009年春季研究発表会  2009 

     More details

  • 平均声に基づく音声合成における話者強調の検討

    日本音響学会2009年春季研究発表会  2009 

     More details

  • A study on stopping criteria for decision-trees in HMM-based speech synthesis

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A technique for cotroling speaking style and emotional expression using model interpolation

    2005 

     More details

  • Hidden semi-Markov model based adaptive training

    2005 

     More details

  • A study on model adaptation and adaptive training using ESAT algorithm in HMM-based speech synthesis

    2005 

     More details

  • 平均声に基づく音声合成における線形変換とMAPに基づく音響モデル学習法

    電子情報通信学会技術研究報告  2006 

     More details

  • A style control technique for speech synthesis using multiple regression HSMM

    Proc. 9th International Conference on Spoken Language Processing  2006 

     More details

  • A technique for controlling voice quality of synthetic speech using multiple regression HSMM

    Proc. 9th International Conference on Spoken Language Processing  2006 

     More details

  • 合成音声のスタイル制御における話者適応の検討

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 重回帰HSMMを用いた音声のスタイル制御における多様性の検討

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 線形変換とMAPに基づく音響モデル学習法の評価

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • MSD-HMMを用いた音声のスタイル識別手法の評価

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

▼display all

Works

  • 擬人化音声対話エージェントツールキットGalateaの公開

    2003

     More details

  • メルケプストラムCV方式に基づく日本語規則音声合成システムの実時間実現

    1984

     More details

  • A Real-Time Realization of Japanese Speech Synthesis-by-Rule System using CV-syllable Mel-Cepstral Parameters

    1984

     More details

Awards

  • 情報・システムソサイエティ活動功労賞

    2010  

     More details

    Country:Japan

    researchmap

  • 電気通信普及財団賞(テレコムシステム技術賞)

    2008  

     More details

    Country:Japan

    researchmap

  • 情報・システムソサイエティ論文賞

    2008  

     More details

    Country:Japan

    researchmap

  • IEICE Best Paper Award

    2001  

     More details

  • 電子情報通信学会猪瀬賞

    2001  

     More details

    Country:Japan

    researchmap

  • 電子情報通信学会論文賞

    2001  

     More details

    Country:Japan

    researchmap

  • IEICE Inose Award

    2001  

     More details

  • 電気通信普及財団賞(テレコムシステム技術賞)

    2001  

     More details

    Country:Japan

    researchmap

  • TELECOM System Technology Prize

    2001  

     More details

  • 電気通信普及財団賞

    1998  

     More details

    Country:Japan

    researchmap

▼display all

Research Projects

  • Speech synthesis with various voice characteristics and speaking styles based of average voice

      More details

    Grant type:Competitive

    researchmap

  • Study on Low Bit-rate Speech Coding

      More details

    Grant type:Competitive

    researchmap

  • Study on Spoken Language Interface

      More details

    Grant type:Competitive

    researchmap

  • Multimodal Speech Synthesis Based on Hidden Markov Models

      More details

    Grant type:Competitive

    researchmap

  • Human motion generation from motion primitives

      More details

    Grant type:Competitive

    researchmap

  • 平均声からの多様な音声合成

      More details

    Grant type:Competitive

    researchmap

  • 隠れマルコフモデルに基づくマルチモーダル音声合成

      More details

    Grant type:Competitive

    researchmap

  • 動作プリミティブからのヒューマンモーション生成

      More details

    Grant type:Competitive

    researchmap

  • 低ビットレート音声符号化に関する研究

      More details

    Grant type:Competitive

    researchmap

  • 音声言語インターフェースに関する研究

      More details

    Grant type:Competitive

    researchmap

▼display all