A Study on Speech Synthesis with Rich Personality Based on Automatic Scoring of Reproduction of Speaker Identity
| Project/Area Number |
24500223
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Ritsumeikan University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2014: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2012: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 声質 / 個人性 / 多様性 / 韻律 / 音声合成 / 音声分析 / スペクトル / パラ言語情報 / 感情 / 話者性 / 重み付きユークリッド距離 |
|---|
| Outline of Final Research Achievements |
This research addresses measurement of personality and analysis of diversity in speech aiming at realizing speech synthesis with rich personalization.
I proposed a new method for measuring the difference of voice quality based on feature parameters of speech. The similarity of voice quality is calculated by weighted Euclidean distance of MFCC parameters which represent spectrum features of speech. I analyzed the relationship between prosodic information and personality perception using synthetic speech in which phonemic information is removed but prosodic information, such as intonation, is preserved. I also analyzed various types of speech which include dialect, character voices in ‘Anime’, announcer voices, emotional voices，and so on.
|
Report
(4 results)
Research Products
(11 results)
