• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

固有声(eigenvoice)に基づいた音声合成---多様な声質の実現を目指して---

Research Project

Project/Area Number 12680380
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionNagoya Institute of Technology

Principal Investigator

KITAMURA Tadashi (2001-2002)  Nagoya Institute of Technology, Faculty of Egnineering, Professor, 大学院・工学研究科, 教授 (60114865)

徳田 恵一 (2000)  名古屋工業大学, 工学部, 助教授 (20217483)

Co-Investigator(Kenkyū-buntansha) MIYAJIMA Chiyomi  Nagoya Institute of Technology, Research Associate, 大学院・工学研究科, 助手 (90335092)
MASUKO Takashi  Tokyo Institute of Technology, Research Associate, 大学院・総合理工学研究科, 助手 (90272715)
KOBAYASHI Takao  Tokyo Institute of Technology, Professor, 大学院・総合理工学研究科, 教授 (70153616)
小林 隆夫  名古屋工業大学, 工学部, 教授 (40186747)
北村 正  名古屋工業大学, 工学部, 教授 (60114865)
Project Period (FY) 2000 – 2002
Project Status Completed (Fiscal Year 2002)
Budget Amount *help
¥3,600,000 (Direct Cost: ¥3,600,000)
Fiscal Year 2002: ¥1,000,000 (Direct Cost: ¥1,000,000)
Fiscal Year 2001: ¥1,200,000 (Direct Cost: ¥1,200,000)
Fiscal Year 2000: ¥1,400,000 (Direct Cost: ¥1,400,000)
KeywordsHNW-based speech synthesys / eigenvoice / voice quality / eigenvoice / 隠れマルコフモデル / 声質変換 / スペクトル包絡 / 基本周波数 / 多空間分布HMM / 音声合成 / メルケプストラム / 主成分分析
Research Abstract

In this research work, we investigate an eigenvoice technique for an HMM-based speech synthesis system which can synthesize speech with various voice qualities. In the eigenvoice technique for very fast speaker adaptation in HMM-based speech recognition, a large number of speaker dependent HMM sets are represented by a few parameters through a dimensionality reduction technique, e.g., PCA. The parameters to be adapted are very few, and the correspondence between the parameters and voice qualities was discussed. Accordingly, we surmise that by applying the eigenvoice technique to the HMM-based speech synthesis system, we can specify voice qualities and synthesize desired voices easily. In this point of view, we proposed an eigenvoice technique for speech synthesis and applied it to the HMM-based speech synthesis system, which models spectrum and FO simultaneously in a unified framework of HMM. As a result, users can define voice qualities by setting a few parameters : weights for the eigenvoices. We conducted subjective evaluation tests to investigate the correspondence between weight values for eigenvoices and voice qualities. The speech synthesis system constructed based the results of the subjective evaluation tests can synthesize speech with various voice qualities and we confirmed the possibility of obtaining desired voice qualities easily by setting the parameters which represent the voice qualities.

Report

(4 results)
  • 2002 Annual Research Report   Final Research Report Summary
  • 2001 Annual Research Report
  • 2000 Annual Research Report
  • Research Products

    (122 results)

All Other

All Publications (122 results)

  • [Publications] 徳田恵一, 益子貴史, 宮崎昇, 小林隆夫: "多空間上の確立分布に基づいたHMM"電子情報通信学会論文誌. vol.J83-D-II, no.7. 1579-1589 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 益子貴史, 徳田恵一, 宮崎昇, 小林隆夫: "多空間確率分布HMMによるピッチパタン生成"電子情報通信学会論文誌. vol.J83-D-II, no.7. 1600-1609 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正: "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"電子情報通信学会論文誌. vol.J83-D-II, no.11. 2099-2107 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda, Takayoshi Yoshimura, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "Speech parameter generation algorithms for HMM-based speech synthesis"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. vol.3. 1315-1318 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "Mixed excitation for HMM-based speech Synthesis"Proceedings of European Conference on Speech Communication and Technology. vol.3. 2263-2266 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Kengo Shichiri, Atsushi Sawabe, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "Eigenvoices for HMM-based speech synthesis"8th International Conference on Spoken Language Processing. 1269-1272 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 沢辺敦, 七里建吾, 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正: "HMM音声合成におけるスペクトル・ピッチへの固有声手法の適用"電子情報通信学会技術研究報告. vol.101,no.325,SP2001-72. 65-72 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 沢辺敦, 七里建吾, 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正: "固有声に基づいたtriphoneによる音声合成"日本音響学会研究発表会講演論文集. vol.1,2-6-9. 299-300 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正: "HMMに基づく音声合成のための励振源モデルの検討"日本音響学会研究発表会講演論文集. vol.1,2-6-8. 297-298 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 沢辺敦, 七里建吾, 吉村貴克, 徳田恵一, 北村正, 益子貴史, 小林隆夫: "固有声手法に基づく音声合成におけるピッチのモデル化"日本音響学会研究発表会. 315-316 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 七里建吾, 徳田恵一, 益子貴史, 小林隆夫, 北村正: "固有声を用いたHMM音声合成における声質評価の検討"日本音響学会2002年秋季研究発表会講演論文集. vol.I,3-10-16. 359-360 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 吉村, 徳田, 益子, 小林, 北村: "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"電子情報通信学会音声研究会資料. SP2001-63. 17-22 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Yoshimura, Masuko, Tokuda, Kobayashi, Kitamura: "Mixed Excitation for HMM-Based Speech Synthesis"Proceedings of EUROSPEECH2001. 779-782 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 吉村, 徳田, 益子, 小林, 北村: "HMMに基づく音声合成における品質改善に関する検討"日本音響学会2001年秋季研究発表会講演論文集. vol.I. 371-372 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 川本真一: "擬人化音声対話エージェントの構築"情報処理学会論文誌. vol.43,no.7. 2249-2263 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 酒向慎司: "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"情報処理学会論文誌. vol.43,no.7. 1382-1391 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 田村正統: "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"電子情報通信学会論文誌. vol.J85-D-11,no.4. 545-553 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Masatsune Tamura: "A training method for average voice model based on shared decision tree context clustering and speaker adaptive training"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. (予定発表). (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Hiroyuki Suzuki: "Speech recognition using voice-characteristic-dependent acoustic models"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. (予定発表). (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda: "An HMM-based speech synthesis system applied to English"2002 IEEE Speech Synthesis Workshop. (CD-ROM). (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Shin-ichi Kawamoto: "Open-source Software for Developing Anthropomorphic Spoken Dialog Agents"International Workshop on LIFELIKE ANIMATED AGENTS Tools, Affective Functions, and Applications. 64-69 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Jun-ichi Yamagishi: "A context clustering technique for average voice model in HMM-based speech synthesis"8th International Conference on Spoken Language Processing. 133-136 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Heiga Zen: "Decision tree distribution tying based on a dimensional split technique"8th International Conference on Spoken Language Processing. 1257-1260 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Shin-ichi Kawamoto: "Freeware for developments of anthropomorphic dialog agent"Third International Conference on Language Resources and Evaluation. (CD-ROM). (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 嵯峨山茂樹: "擬人化音声対話エージェントツールキットGalatea"情報処理学会研究報告. vol.2003. 57-64 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 山岸順一: "平均声モデル構築におけるコンテキストクラスタリングと話者適応学習の検討"電子情報通信学会技術研究報告. vol.102,no.292. 5-10 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 川本 真一: "カスタマイズが容易な擬人化音声対話エージェント"Interaction2002. 61-62 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 川本真一: "擬人化音声対話エージェントツールキットの基本設計"情報処理学会研究報告. vol.2002,no.10. 61-66 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 七里建吾: "固有声手法を用いたHMMに基づく任意の音声合成システムの検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 275-276 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 江本喜久男: "自動ラベリングのためのMSD-HMMを用いたアクセント型認識"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 369-370 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 水谷伸晃: "HMMに基づいた単位接続型音声合成における継続長コストの導入"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 245-246 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 都築亮介: "HMM音声合成における感情表現のモデル化に関する検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 269-270 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 岸本由加: "HMM音声合成のためのポストフィルタ係数の自動決定"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 243-244 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 片岡俊介: "HMM音声合成における決定木のバックオフによる品質改善の検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 239-240 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 板谷洋平: "DAEMアルゴリズムを用いた話者認識のためのGMM学習法"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 115-116 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 全炳河: "動的特徴量を含んだHMMより導出されるトラジェクトリモデル"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 13-14 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 全炳河: "言語モデルからの文生成による音声合成コーパス用テキスト設計の検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 257-258 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 徳田恵一: "律生成HMMのための学習データ作成ツール"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 259-260 (2003)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 山岸順一: "話者適応のための平均声モデル学習法の検討"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 351-352 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda: "HMM-based approach to English speech synthesis"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 357-358 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 全炳河: "決定木による音素コンテキスト・次元・状態位置の同時クラスタリング"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 39-40 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 水谷伸晃: "HMMに基づいた単位接続型音声合成"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 241-242 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 鈴木浩之: "声質を考慮した音響モデルによる音声認識"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 37-38 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 岸本由加: "HMM音声合成のためのポストフィルタリング"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 279-280 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 石川ちさと: "HMM歌声合成における音韻・音高の同時モデル化"第1回情報科学フォーラムForum on Information Technology (FIT2002). 237-238 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi and K.Kitamura: "Speaker interpolation for HMM-based speech synthesis system"The Journal of the Acoustical Society of Japan (E). vol.21,no.4. 199-206 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Kazuhito Koishida, Keiichi Tokuda, Takashi Masuko and Takao Kobayashi: "Vector quantization of speech spectral parameters using statistics of static and dynamic features"IEICE Trans.Inf.& Syst.. vol.E84-D,no.10. 1427-1434 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Junichi Yamagishi, Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi: "A Context Clustering Technique for Average Voice Models"IEICE Trans.Inf.& Syst.. vol.E86-D,no.3. 534-542 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Junichi Yamagishi, M.Tamura, T.Masuko, K.Tokuda and T.Kobayashi: "Atraining method of average voice model for HMM-based speech synthesis"IEICE Trans.Fundamentals. (accepted).

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda, Takayoshi Yoshimura, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "Speech parameter generation algorithms for HMM-based speech synthesis"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. vol.3. 1315-1318 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takashi Masuko, Keiichi Tokuda and Takao Kobayashi: "Imposture using synthetic speech against speaker verification based on spectrum and pitch"International Conference on Spoken Language Processing (ICSLP2000/ INTERSPEECH 2000). vol.III. 302-305 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Shinji Sako, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "HMM-based text-to-audio-visual speech synthesis (invited session)"International Conference on Spoken Language Processing (ICSLP2000/ INTERSPEECH 2000). vol.III. 25-28 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Masatsune Tamura, Takashi Masuko, Keiichi Tokuda and Takao Kobayashi: "Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). vol.2. 805-808 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi: "Text-to-speech synthesis with arbitrary speaker's voice from average voice"Proceedings of European Conference on Speech Communication and Technology. vol.1. 345-348 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takayuki Satoh, Takashi Masuko, Takao Kobayashi, Keiichi Tokuda: "A robust speaker verification system against imposture using an HMM-based speech synthesis system"Proceedings of European Conference on Speech Communication and Technology. vol.2. 759-762 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "Mixed excitation for HMM-based speech Synthesis"Proceedings of European Conference on Speech Communication and Technology. vol.3. 2263-2266 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Shin-ichi Kawamoto, Hiroshi Shimodaira, Shigeki Sagayama, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Akihiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro: "Developments of anthropomor-phic dialog agent : A plan and development and its significance"Interna-tional Workshop on Information Presentation and Natural Multimodal Dialogue. (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Shin-ichi Kawamoto, Hiroshi Shimodaira, Shigeki Sagayama, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Akihiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro: "Freeware for developments of an-thropomorphic dialog agent"Third International Conference on Language Resources and Evaluation. (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Heiga Zen, Keiichi Tokuda, Tadashi Kitamura: "Decision tree distribution tying based on a dimensional split technique"8th International Conference on Spoken Language Processing. 1257-1260 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Kengo Shichiri, Atsushi Sawabe, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura: "Eigenvoices for HMM-based speech synthesis"8th International Conference on Spoken Language Processing. 1269-1272 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Jun-ichi Yamagishi, Masatsune Tamura, Takashi Masuko, Takao Kobayashi: "A context clustering technique for average voice model in HMM-based speech synthesis"8th International Conference on Spoken Language Processing. 133-136 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Shin-ichi Kawamoto, Hiroshi Shimodaira, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katsunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Atsuhiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro, Shigeki Sagayama: "Open-source Software for Developing Anthropomorphic Spoken Dialog Agents"International Workshop on LIFELIKE ANIMATED AGENTS Tools, Affective Functions, and Applications. 64-69 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda, Zen Heiga, Alan W.Black: "An HMM-based speech synthesis system applied to English"2002 IEEE Speech Synthesis Workshop. (CD-ROM proceedings). (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takahiro Hoshiya, Shinji Sako, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, Heiga Zen: "Improving the performance of HMM-based very low bitrate speech coding"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). vol.1. 800-803 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Hiroyuki Suzuki, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura: "Speech recognition using voice-characteristic-dependent acoustic models"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). vol.1. 740-743 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Junichi Yamagishi, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi: "A training method for average voice model based on shared decision tree context clustering and speaker adaptive training"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). vol.1. 716-719 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda, Heiga Zen, Tadashi Kitamura, Fernando Gil Vianna Resende Junior: "A Trajectory Model Derived from HMMs Imposing Explicit Relationship between Static and Dynamic Features"Proceedings of European Conference on Speech Communication and Technology. (accepted). (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Ranniery da Silva Mala, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Fernando Gil Vianna Resende Junior: "Towards the Development of a Brazilian Portuguese Text-to-Speech System Based on HMM (accepted)"Proceedings of European Conference on Speech Communication and Technology. (accepted). (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Heiga Zen, Keiichi Tokuda, Tadashi Kitamura: "Decision Tree-based Simultaneous Clustering of Phonetic Contexts, Dimensions, and State Positions for Acoustic Modeling"Proceedings of European Conference on Speech Communication and Technology. (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Takashi Masuko, Takao Kobayashi, Keiichi Tokuda: "Imposture using synthetic speech against text-prompted speaker verification based on spectrum and pitch"IEICE Technical report. vol.100,no.392,SP2000-71. 21-26 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda, Heiga Zen, A.W.Black: "HMM-based approach to English speech synthesis"Proc.of Biannual Conference of Acoustical Society of Japan. vol.I,3-10-15. 357-358 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] Keiichi Tokuda, Takashi Mausko, Noboru Miyazaki, Takao Kobayashi: "Multispace probability distribution HMM"IEICE Trans.Information and Systems. vol.E85-D,no.3. 455-464 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2002 Final Research Report Summary
  • [Publications] 川本真一: "擬人化音声対話エージェントの構築"情報処理学会論文誌. vol.43 no.7. 2249-2263 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 酒向慎司: "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"情報処理学会論文誌. vol.43 no.7. 1382-1391 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 田村正統: "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"電子情報通信学会論文誌. vol.185-D-11 no.4. 545-553 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Junichi Yamagishi: "A training method for average voice model based on shared decision tree context clustering and speaker adaptive training"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. vol.1. 716-719 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] Hiroyuki Suzuki: "Speech recognition using voice-characteristic-dependent acoustic models"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. vol.1. 740-743 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] Keiichi Tokuda: "An HMM-based speech synthesis system applied to English"2002 IEEE Speech Synthesis Workshop. (CD-ROM). (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Shin-ichi Kawamoto: "Open-source Software for Developing Anthropomorphic Spoken Dialog Agents"International Workshop on LIFELIKE ANIMATED AGENTS Tools, Affective Functions, and Applications. 64-69 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Jun-ichi Yamagishi: "A context clustering technique for average voice model in HMM-based speech synthesis"8th International Conference on Spoken Language Processing. 133-136 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Kengo Shichiri: "Eigenvoices for HMM-based speech synthesis"8th International Conference on spoken Language Processing. 1269-1272 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Heiga Zen: "Decision tree distribution tying based on a dimensional split technique"8th International Conference on spoken Language Processing. 1257-1260 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Shin-ichi Kawamoto: "Freeware for developments of anthropomorphic dialog agent"Third International Conference on Language Resources and Evaluation. (CD-ROM). (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 嵯峨山茂樹: "擬人化音声対話エージェントツールキットGalatea"情報処理学会研究報告. vol.2003. 57-64 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 山岸順一: "平均声モデル構築におけるコンテキストクラスタリングと話者適応学習の検討"電子情報通信学会技術研究報告. vol.102 no.292. 5-10 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 川本真一: "カスタマイズが容易な擬人化音声対話エージェント"Interaction2002. 61-62 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 川本 真一: "擬人化音声対話エージェントツールキット基本設計"情報処理学会研究報告. vol.2002, no.10. 61-66 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 七里建吾: "固有声手法を用いたHMMに基づく任意の声質合成システムの検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 275-276 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 江本喜久男: "自動ラベリングのためのMSD-HMMを用いたアクセント型認識"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 369-370 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 水谷伸晃: "HMMに基づいた単位接続型音声合成における継続長コストの導入"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 245-246 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 都築亮介: "HMM音声合成における感情表現のモデル化に関する検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 269-270 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 岸本由加: "HMM音声合成のためのポストフィルタ係数の自動決定"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 243-244 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 片岡俊介: "HMM音声合成における決定木のバックオフによる品質改善の検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 239-240 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 板谷洋平: "DAEMアルゴリズムを用いた話者認識のためのGMM学習法"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 115-116 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 全〓河: "動的特徴量を含んだHMMより導出されるトラジェクトリモデル"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 13-14 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 全〓河: "言語モデルからの文生成による音声合成コーパス用テキスト設計の検討"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 257-258 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 徳田恵一: "律生成HMMのための学習データ作成ツール"日本音響学会2003年秋季研究発表会講演論文集. vol.I. 259-260 (2003)

    • Related Report
      2002 Annual Research Report
  • [Publications] 山岸順一: "話者適応のための平均声モデル学習法の検討"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 351-352 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] Keiichi Tokuda: "HMM-based approach to English speech synthesis"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 357-358 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 七里建吾: "固有声を用いたHMM音声合成における声質評価の検討"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 359-360 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 全〓河: "決定木による音素コンテキスト・次元・状態位置の同時クラスタリング"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 39-40 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 水谷伸晃: "HMMに基づいた単位接続型音声合成"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 241-242 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 鈴木浩之: "声質を考慮した音響モデルによる音声認識"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 37-38 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 岸本由加: "HMM音声合成のためのポストフィルタリング"日本音響学会2002年秋季研究発表会講演論文集. vol.I. 279-280 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 石川ちさと: "HMM歌声合成における音韻・音高の同時モデル化"第1回情報科学技術フォーラムForum on Information Technology (FIT2002). 237-238 (2002)

    • Related Report
      2002 Annual Research Report
  • [Publications] 沢辺, 七里, 吉村, 徳田, 北村, 益子, 小林: "固有声手法に基づく音声合成におけるピッチのモデル化"日本音響学会2001年秋季研究発表会 講演論文集. I. 315-316 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 吉村, 徳田, 益子, 小林, 北村: "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"電子情報通信学会音声研究会資料. SP2001-63. 17-22 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 沢辺, 七里, 吉村, 徳田, 益子, 小林, 北村: "HMM音声合成におけるスペクトル・ピッチへの固有声手法の適用"電子情報通信学会音声研究会資料. SP2001-72. 65-72 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] Yoshimura, Masuko, Tokuda, Kobayashi, Kitamura: "Mixed Excitation for HMM-based Speech Synthesis"Proceedings of EUROSPEECH2001. 779-782 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 吉村, 徳田, 益子, 小林, 北村: "HMMに基づく音声合成における品質改善に関する検討"日本音響学会2001年秋季研究発表会 講演論文集. I. 371-372 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 益子貴史: "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"信学論(D-II). vol.J83-D-II,no.12. 2509-2516 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 吉村貴克: "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"信学論(D-II). vol.J83-D-II.no.11. 2099-2107 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 益子貴史: "多空間確率分布HMMによるピッチパタン生成"信学論(D-II). vol.J83-D-II,no.7. 1600-1609 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 徳田恵一: "多空間上の確率分布に基づいたHMM"信学論(D-II). vol.J83-D-II,no.7. 1579-1589 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] K.Tokuda: "Speech parameter generation algorithms for HMM-based speech synthesis"Proccedings of International Conference on Acoustics, Speech, and Signal Processing. vol.3. 1315-1318 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 徳田恵一: "HMMによる音声合成の基礎"信学技報. vol.100.no.392. 43-50 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 吉村貴克: "HMMに基づく音声合成のための励振源モデルの検討"日本音響学会講論集. (発表予定). (2001)

    • Related Report
      2000 Annual Research Report
  • [Publications] 沢辺敦: "固有声に基づいたtriphoneによる音声合成"日本音響学会講論集. (発表予定). (2001)

    • Related Report
      2000 Annual Research Report
  • [Publications] 田村正統: "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"日本音響学会講論集. (発表予定). (2001)

    • Related Report
      2000 Annual Research Report
  • [Publications] 熊倉俊之: "HMM音声合成システムのためのテキスト処理部の構築"日本音響学会講論集. (発表予定). (2001)

    • Related Report
      2000 Annual Research Report
  • [Publications] 吉村貴克: "HMMに基づく音声合成システムの自動構築"日本音響学会講論集. vol.1. 233-234 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 田村正統: "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"日本音響学会講論集. vol.1. 319-320 (2000)

    • Related Report
      2000 Annual Research Report

URL: 

Published: 2000-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi