| Presentation | 2016-01-14 Pitch-synchronous band group delay vocoder for high quality speech synthesis Masatsune Tamura, Ryo Morinaka, Masahiro Morita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper presents a speech analysis and synthesis method that can precisely synthesize speech waveforms for high quality statistical parametric speech synthesis. The proposed method is based on pitch-synchronous analysis. A power spectrum, aperiodicity measure, pitch, and phase spectrum of each analysis frame is represented by a mel LSP (MLSP), band aperiodicity (BAP), log fundamental frequency (LF0) and new band group delay with compensation parameter (BGRDC), respectively. The BGRDC consists of a band group delay parameter which represents a mean time of each frequency band and a compensation parameter which recovers a phase spectrum at the boundary of the band. We also propose a band group delay vocoder that enables fast generation of speech waveforms by using time domain excitation generation and a vocal tract filter. We show that the proposed method can precisely generate speech waveforms by objective and subjective evaluations. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speech Analysis / Speech Synthesis / Vocoder / Pitch-synchronous analysis / Phase spectrum / Group delay |
| Paper # | SP2015-91 |
| Date of Issue | 2016-01-07 (SP) |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2016/1/14(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Sunpian Kawasaki |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Synthesis, Generation, Prosody, etc. |
| Chair | Kazunori Mano(Shibaura Inst. of Tech.) |
| Vice Chair | Norihide Kitaoka(Tokushima Univ.) |
| Secretary | Norihide Kitaoka(Tokyo City Univ.) |
| Assistant | Takashi Nose(Tohoku Univ.) / Taichi Asami(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Speech |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Pitch-synchronous band group delay vocoder for high quality speech synthesis |
| Sub Title (in English) | |
| Keyword(1) | Speech Analysis |
| Keyword(2) | Speech Synthesis |
| Keyword(3) | Vocoder |
| Keyword(4) | Pitch-synchronous analysis |
| Keyword(5) | Phase spectrum |
| Keyword(6) | Group delay |
| 1st Author's Name | Masatsune Tamura |
| 1st Author's Affiliation | Toshiba Corporation(Toshiba) |
| 2nd Author's Name | Ryo Morinaka |
| 2nd Author's Affiliation | Toshiba Corporation(Toshiba) |
| 3rd Author's Name | Masahiro Morita |
| 3rd Author's Affiliation | Toshiba Corporation(Toshiba) |
| Date | 2016-01-14 |
| Paper # | SP2015-91 |
| Volume (vol) | vol.115 |
| Number (no) | SP-392 |
| Page | pp.pp.33-38(SP), |
| #Pages | 6 |
| Date of Issue | 2016-01-07 (SP) |