| Project/Area Number |
14380160
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
TOKUDA Keikhi Nagoya Institute of Technology, Graduate School of Engineering, Professor, 工学研究科, 教授 (20217483)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KITAMURA Tadashi Nagoya Institute of Technology, Graduate School of Engineering, Professor, 工学研究科, 教授 (60114865)
KOBAYASHI Takao Tokyo Institute of Technology, Interdisciplinary Graduate School of Science and Engineering, Professor, 大学院・総合理工学研究科, 教授 (70153616)
MASUDA Takashi Tokyo Institute of Technology, Interdisciplinary Graduate School of Science and Engineering, Research Associate, 大学院・総合理工学研究科, 助手 (90272715)
|
|---|
| Project Period (FY) |
2002 – 2004
|
| Project Status |
Completed (Fiscal Year 2004)
|
| Budget Amount *help |
¥9,300,000 (Direct Cost: ¥9,300,000)
Fiscal Year 2004: ¥2,900,000 (Direct Cost: ¥2,900,000)
Fiscal Year 2003: ¥3,000,000 (Direct Cost: ¥3,000,000)
Fiscal Year 2002: ¥3,400,000 (Direct Cost: ¥3,400,000)
|
|---|
| Keywords | speech synthesis / voice quality / emotional speech / HMM-based speech synthesis / labeling / automatic voice bulding / PLEd |
|---|
| Research Abstract |
The increasing availability of large speech databases makes it possible to construct speech synthesis systems, which are referred to as data-driven or corpus-based approach, by applying statistical learning algorithms. These systems, which can be automatically trained, not only generate natural and high quality synthetic speech but also can reproduce voice characteristics of the original speaker. However, to make the whole voice building process fully-automatic, we need to construct speech databases in an automatic way. In this research work, we investigate automatic voice building techniques for an HMM-based speech synthesis system which can synthesize speech with various voice qualities. First, we implemented an GUI-based labeling tool, called PLEd (Prosody and Linguistic Label Editor). Then, in order to construct an automatic voice building system, we have developed an automatic accent labeling technique. It has been shown that by using the developed system, we have successfully label accent information.
|
