ヒューマノイド音声対話システムのための話し言葉音声合成に関する研究

2010 年度 研究成果報告書

• 研究課題/領域番号: 21800020
• 研究種目: 研究活動スタート支援
• 配分区分: 補助金
• 研究分野: 知覚情報処理・知能ロボティクス
• 研究機関: 東京工業大学
• 研究代表者: 能勢 隆 東京工業大学, 大学院・総合理工学研究科, 助教 (90550591)
• 研究期間 (年度): 2009 – 2010
• キーワード: テキスト音声合成 / 隠れマルコフモデル / 話し言葉音声 / 話者適応 / HMM音声合成 / ヒューマノイドロボット / 音声対話システム / 声質変換

研究概要

ヒューマノイド音声対話システムの実現に向けた話し言葉音声合成のための基盤技術として、(1)統計モデルに基づく話し言葉音声合成の検討、(2)統計モデルに基づく不特定話者声質変換の検討、(3)音声合成における音韻・韻律コンテキストの詳細な評価、を行った。

研究成果

• [雑誌論文] HMM-based voice conversion using quantized F0 context (2010)
  • 著者名/発表者名: Takashi Nose, Yuhei Ota, Takao Kobayashi
  • 雑誌名: IEICE Trans.on Information and Systems D vol.E93-9 ページ: 2483-2490
  • 査読あり
• [雑誌論文] Evaluation of prosodic contextual factors for HMM-based speech synthesis (2010)
  • 著者名/発表者名: Shuji Yokomizo, Takashi Nose, Takao Kobayashi
  • 雑誌名: Proc.11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 ページ: 430-433
  • 査読あり
• [雑誌論文] Conversational spontaneous speech synthesis using average voice model (2010)
  • 著者名/発表者名: Tomoki Koriyama, Takashi Nose, Takao Kobayashi
  • 雑誌名: Proc.11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 ページ: 853-856
  • 査読あり
• [雑誌論文] Speaker-independent HMM-based voice conversion using quantized fundamental frequency (2010)
  • 著者名/発表者名: Takashi Nose, Takao Kobayashi
  • 雑誌名: Proc.11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 ページ: 1724-1727
  • 査読あり
• [雑誌論文] HMM-based robust voice conversion using adaptive F0 quantization (2010)
  • 著者名/発表者名: Takashi Nose, Takao Kobayashi
  • 雑誌名: Proc.7th ISCA Workshop on Speech Synthesis, SSW7-2010 ページ: 80-85
  • 査読あり
• [雑誌論文] A rapid model adaptation technique for emotional speech recognition with style estimation based on multiple-regression HMM (2010)
  • 著者名/発表者名: Yusuke Ijima, Takashi Nose, Makoto Tachibana, Takao Kobayashi
  • 雑誌名: IEICE Trans.on Information and Systems D vol.E93-1 ページ: 107-115
  • 査読あり
• [雑誌論文] A technique for estimating intensity of emotional expressions and speaking styles in speech based on multiple-regression HSMM (2010)
  • 著者名/発表者名: Takashi Nose, Takao Kobayashi
  • 雑誌名: IEICE Trans.on Information and Systems D vol.E93-1 ページ: 116-124
  • 査読あり
• [雑誌論文] HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model (2009)
  • 著者名/発表者名: Takashi Nose, Koujirou Ooki, Takao Kobayashi
  • 雑誌名: Proc.2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ページ: 4622-4625
  • 査読あり
• [雑誌論文] Speaking style adaptation for spontaneous speech recognition using multiple-regression HMM (2009)
  • 著者名/発表者名: Yusuke Ijima, Takeshi Matsubara, Takashi Nose, Takao Kobayashi
  • 雑誌名: Proc.10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 ページ: 552-555
  • 査読あり
• [雑誌論文] HMM-based speaker characteristics emphasis using average voice model (2009)
  • 著者名/発表者名: Takashi Nose, Junichi Asada, Takao Kobayashi
  • 雑誌名: Proc.10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 ページ: 2631-2634
  • 査読あり
• [雑誌論文] A robust speaker-adaptive HMM-based text-to-speech synthesis (2009)
  • 著者名/発表者名: Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhenhua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, Steve Renals
  • 雑誌名: IEEE Trans.on Audio, Speech, and Language Processing vol.17, 6 ページ: 1208-1230
  • 査読あり
• [雑誌論文] Emotional speech recognition based on style estimation and adaptation with multiple-regression HMM (2009)
  • 著者名/発表者名: Yusuke Ijima, Makoto Tachibana, Takashi Nose, Takao Kobayashi
  • 雑誌名: Proc.2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 ページ: 4157-4160
  • 査読あり
• [学会発表] Speaker-independent HMM-based voice conversion using quantized fundamental frequency (2010)
  • 著者名/発表者名: Takashi Nose, Takao Kobayashi
  • 学会等名: Proc.11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
  • 発表場所: Makuhari, Japan.
  • 年月日: 2010-09-29
• [学会発表] Conversational spontaneous speech synthesis using average voice model (2010)
  • 著者名/発表者名: Tomoki Koriyama, Takashi Nose, Takao Kobayashi
  • 学会等名: Proc.11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
  • 発表場所: Makuhari, Japan.
  • 年月日: 2010-09-28
• [学会発表] Evaluation of prosodic contextual factors for HMM-based speech synthesis (2010)
  • 著者名/発表者名: Shuji Yokomizo, Takashi Nose, Takao Kobayashi
  • 学会等名: Proc.11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
  • 発表場所: Makuhari, Japan.
  • 年月日: 2010-09-27
• [学会発表] HMM-based robust voice conversion using adaptive F0 quantization (2010)
  • 著者名/発表者名: Takashi Nose, Takao Kobayashi
  • 学会等名: Proc.7th ISCA Workshop on Speech Synthesis, SSW7-2010
  • 発表場所: Kyoto, Japan.
  • 年月日: 2010-09-22
• [学会発表] HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model (2010)
  • 著者名/発表者名: Takashi Nose, Koujirou Ooki, Takao Kobayashi
  • 学会等名: 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
  • 発表場所: Dallas, USA.
  • 年月日: 2010-03-17
• [学会発表] HMM-based speaker characteristics emphasis using average voice model (2009)
  • 著者名/発表者名: Takashi Nose, Junichi Asada, Takao Kobayashi
  • 学会等名: Proc.10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009
  • 発表場所: Brighton, U.K.
  • 年月日: 2009-09-10
• [学会発表] Speaking style adaptation for spontaneous speech recognition using multiple-regression HMM (2009)
  • 著者名/発表者名: Yusuke Ijima, Takeshi Matsubara, Takashi Nose, Takao Kobayashi
  • 学会等名: Proc.10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009
  • 発表場所: Brighton, U.K.
  • 年月日: 2009-09-07
• [学会発表] Emotional speech recognition based on style estimation and adaptation with multiple-regression HMM (2009)
  • 著者名/発表者名: Yusuke Ijima, Makoto Tachibana, Takashi Nose, Takao Kobayashi
  • 学会等名: Proc.2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, 4157-4160
  • 発表場所: Taipei, Taiwan.
  • 年月日: 2009-04-21