Study on speech synthesis for humanoid spoken dialog system

2010 Fiscal Year Final Research Report

• Project/Area Number: 21800020
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Tokyo Institute of Technology
• Principal Investigator: NOSE Takashi Tokyo Institute of Technology, 大学院・総合理工学研究科, 助教 (90550591)
• Project Period (FY): 2009 – 2010
• Keywords: 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

Research Abstract

Two novel techniques and an investigation were presented that is key technologies of speech synthesis for the development of humanoid spoken dialog system as follows. (1) Spontaneous speech synthesis based on statistical parametric modeling (2) Speaker-independent voice conversion based on statistical parametric modeling. (3) Investigation of phonetic and prosodic contextual factors in speech synthesis.

Research Products

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