| Presentation | 2004/12/14 A Synthesis of Emotional Speech Using Eigenspeech Shinya MORI, Tsuyoshi MORIYAMA, Shinji OZAWA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recent progress in hardware made tex-to-speech system general in wave form splicing. Technology to implement variations in speech, such as phonemic environment, emotion and speaker, is required. The main difficulty in the existing technology is that they require the same number of wave forms as the number of varieties considered. Thus, as the number of factors increases, the more wave forms the system requires. Furthermore, wave forms not stored in the database cannot be generated in principle. We propose a method to synthesize emotional speech from arbitrary text using principal component analysis(PCA). Developing the statistical model from the varience of the speech parameters by PCA, prosodic parameters of the target speech can be generated efficiently. Synthetic speech of a sentense is generated by concatenating the subphrases synthesized separately where emotional information has been generaged from the model proposed. We confirmed the effectiveness of our method by our examining the result of principal component analysis and the quality evaluation of synthesized speech generaged by our statistical model toreport. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech synthesis / emotion / principal component analysis / PSOLA |
| Paper # | NLC2004-68,SP2004-108 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2004/12/14(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Synthesis of Emotional Speech Using Eigenspeech |
| Sub Title (in English) | |
| Keyword(1) | speech synthesis |
| Keyword(2) | emotion |
| Keyword(3) | principal component analysis |
| Keyword(4) | PSOLA |
| 1st Author's Name | Shinya MORI |
| 1st Author's Affiliation | Keio University() |
| 2nd Author's Name | Tsuyoshi MORIYAMA |
| 2nd Author's Affiliation | Keio University |
| 3rd Author's Name | Shinji OZAWA |
| 3rd Author's Affiliation | Keio University |
| Date | 2004/12/14 |
| Paper # | NLC2004-68,SP2004-108 |
| Volume (vol) | vol.104 |
| Number (no) | 539 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |