| Presentation | 2002/1/17 Using start/end timings of spectral transitions between phonemes in concatenative speech synthesis Toshio HIRAI, Seiichi TENPAKU, Kiyohiro SHIKANO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The definition of "phoneme boundary timing" in a speech corpus affects the quality of concatenative speech synthesis systems. For example, if the required phoneme environment is not matched by the selected one in speech unit selection, the quality may be degraded. In this report, a dynamic segment boundary definition is proposed. A transition period between adjacent phonemes is skipped if the required and realized phoneme environments are different. For a listening test to compare the naturalness of previous/proposed methods, 100 Japanese place names were selected randomly and synthesized. The ratio of naturalness was one to four (previous-v.s. proposed-). The proposed method is especially effective for environment mismatch of nasals, liquid, and voiceless fricatives. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speech synthesis / Spectral transition between phonemes / Label / Concatenative speech synthesis system |
| Paper # | 2001-SP-119 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2002/1/17(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 | Speech (SP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Using start/end timings of spectral transitions between phonemes in concatenative speech synthesis |
| Sub Title (in English) | |
| Keyword(1) | Speech synthesis |
| Keyword(2) | Spectral transition between phonemes |
| Keyword(3) | Label |
| Keyword(4) | Concatenative speech synthesis system |
| 1st Author's Name | Toshio HIRAI |
| 1st Author's Affiliation | Arcadia, Inc. : Nara Institute of Science and Technology() |
| 2nd Author's Name | Seiichi TENPAKU |
| 2nd Author's Affiliation | Arcadia, Inc. |
| 3rd Author's Name | Kiyohiro SHIKANO |
| 3rd Author's Affiliation | Nara Institute of Science and Technology |
| Date | 2002/1/17 |
| Paper # | 2001-SP-119 |
| Volume (vol) | vol.101 |
| Number (no) | 603 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |