2011 Fiscal Year Final Research Report
Expressive Multi-language Speech Synthesis Based on the Generation Process Model and Its Use for Automatic Speech Translation
| Project/Area Number |
21300061
|
|---|
| 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 | The University of Tokyo |
|---|
Principal Investigator |
HIROSE Keikichi 東京大学, 大学院・情報理工学系研究科, 教授 (50111472)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
峯松 信明 東京大学, 情報理工学系研究科, 准教授 (90273333)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
河合 剛 北海道大学, メディア・コミュニケーション研究院, 准教授 (70312981)
|
|---|
| Project Period (FY) |
2009 – 2011
|
| Keywords | 生成過程モデル / 基本周波数パターン / コーパスベース韻律制御 / 音声自動翻訳 / 談話焦点 / HMM音声合成 / 声質と調子 / 音声モーフィング |
|---|
| Research Abstract |
A unified study on prosody control for multi-languages was conductedbased on the generation process model of fundamental frequency contours(F_0 model). We developeda method of prosody adaptation, where differences in F_0 model commands were learned from parallelspeech corpus and were applied to baseline speech. Focus control, style conversion and voiceconversion were realized. Furthermore, by approximating F_0 contours of training speech corpusand/or generated F_0 contours using the F_0 model, we improved the quality of synthetic speech by theHMM-based speech synthesis. Also, we added focus control. Based on the above results, experiments were conducted on conveying discourse information and intentions in speech Translation.
|
