Speech synthesis with communicative prosody driven by the impressions of output lexicons
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, 理工学術院, 教授 (70339737)
|
Co-Investigator(Kenkyū-buntansha) |
小林 哲則 早稲田大学, 理工学部, 教授 (30162001)
誉田 雅彰 (誉田 雅章) 早稲田大学, スポーツ科学学術院, 教授 (90367095)
|
Co-Investigator(Renkei-kenkyūsha) |
KOBAYASHI Tetsunori 早稲田大学, 理工学術院, 教授 (30162001)
NONDA Masaaki 早稲田大学, スポーツ科学学術院, 教授 (90367095)
|
Project Period (FY) |
2006 – 2009
|
Project Status |
Completed (Fiscal Year 2009)
|
Budget Amount *help |
¥18,280,000 (Direct Cost: ¥14,800,000、Indirect Cost: ¥3,480,000)
Fiscal Year 2009: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2008: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2007: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2006: ¥3,200,000 (Direct Cost: ¥3,200,000)
|
Keywords | 音声情報処理 / 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 |
A scheme for communicative prosody generation was proposed to synthesize speech needed for conversational purposes. Using the correlation between communicative prosody and impression attributes of lexicons constituting output, the proposed scheme enables prosody control for conversational speech output. Perceptual experiments showed the superiority of the speech synthesized with the proposed communicative prosody to the conventional one with reading style prosody. Further application to Chinese and English speech synthesis and the reverse technology of impression extraction from speech clarified the usefulness of the proposed approach.
|
Report
(6 results)
Research Products
(43 results)