Communicative speech synthesis using impression attributes of output lexicons

2008 Fiscal Year Self-evaluation Report

• Project/Area Number: 18300063
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Waseda University
• Principal Investigator: SAGISAKA Yoshinori Waseda University, 国際情報通信研究科, 教授 (70339737)
• Project Period (FY): 2006 – 2009
• Keywords: 音声合成 / 韻律制御 / 対話音声 / イントネーション / 基本周波数 / パラ言語情報

Research Abstract

本研究では、発話毎の多様性を実現した、自然性の高い対話音声の合成出力を目的とし、対話音声独自の韻律変化とその要因を解明する。また、対話音声合成を可能とする入力情報の特定、抽出を行う。このため、基本周波数制御生成モデルを中心とした韻律制御モデルを導出する。また、実用音声対話システム、他言語への適応を考えた技術の一般化を追求する。

Research Products

• [Journal Article] Towards Computing Phonetics (2008)
  • Author(s): Y. SAGISAKA
  • Journal Title: 中国語音学報 Vol.1 Pages: 23-37
  • Peer Reviewed
• [Presentation] Communicative prosody processing for synthesis and recognition of para-linguistic information (2008)
  • Author(s): Y. Sagisaka, Y. Greenberg, K. Li, M. Zhu, M. Tsuzaki and H. Kato
  • Organizer: International Conference on Computer Applications
  • Place of Presentation: Yangon
  • Year and Date: 20080200
• [Presentation] Corpus-based speechsyn thesis from reading speech to communicative speech (2008)
  • Author(s): Y. Sagisaka
  • Organizer: ISCA Workshop onSpoken Language Technologies forUnder-resourced languages
  • Place of Presentation: Hanoi
  • Year and Date: 2008-06-05
• [Presentation] Automatic extraction of paralinguistic information from communicative speech (2007)
  • Author(s): Mingzhao Zhu, Ke Li, Y. Greenberg and Y. Sagisaka
  • Organizer: Proc. the 7th Symposium on Natural Language Processing
  • Place of Presentation: Pattaya
  • Year and Date: 20071200
• [Presentation] Inter-language prosodic style modification experiment using word impression vectorfor communicative speech generation (2007)
  • Author(s): K. Li, Y. Greenberg and Y. Sagisaka
  • Organizer: Proc. Interspeech
  • Place of Presentation: Antwerp
  • Year and Date: 20070800
• [Presentation] A trial of communicative prosody generation basedon control characteristic of one word utterance observed in real conversational speech (2006)
  • Author(s): Y.Greenberg, N.Shibuya, M.Tsuzaki, H.Kato, Y.Sagisaka
  • Organizer: Proc. Speech prosody
  • Place of Presentation: Dresden
  • Year and Date: 20060500
• [Book] in NATO Security through Science Series E : Human and Societal Dynamics Vol.8 The Fundamentals of Verbal and Non-verbal Communication and the Biometric Issue (2007)
  • Author(s): K.Li , Y Greenberg, N.Shibuya, N.Campbell, Y.Sagisaka
  • Total Pages: 179-183
  • Publisher: IOS Press On the analysis of F0 control characteristics of nonverbal utterances and its application to communicative prosody generation
• [Book] 「文法と音声V」所載「語彙情報を用いた会話韻律生成について」 (2006)
  • Author(s): 匂坂、グリンバーグ、山下
  • Total Pages: 135-145
  • Publisher: くろしお出版