| Presentation | 2010-06-11 EA2010-37 Proposal on a high-quality speech analysis and synthesis method to develop a singing synthesis system Masanori MORISE, Kota NAKANO, Takanobu NISHIURA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A new voice analysis and synthesis system is proposed to synthesize natural singing voices. The proposed system consists of two methods to estimate the fundamental frequency (FO) and the spectral envelope. The conventional vocoder synthesizes the unvoiced sound based on the estimated parameters and the white noise as the excitation signal. However, singing voice synthesis does generally not require to control the unvoiced sound. The control of the pitch and the spectral envelope of the voiced sound is only required for singing voice synthesis. The proposed system utilizes the input waveform of the unvoiced sound directly to improve the sound quality. This is the hybrid vocoder based on the parameters and the waveform. In this paper, a spectral envelope estimation method is proposed to synthesize the high-quality voice. The experiments are conducted to demonstrate the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Voice analysis / Spectral envelope / Singing voice synthesis / Pitch synchronous analysis |
| Paper # | EA2010-37 |
| Date of Issue |
| Conference Information | |
| Committee | EA |
|---|---|
| Conference Date | 2010/6/3(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 | Engineering Acoustics (EA) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | EA2010-37 Proposal on a high-quality speech analysis and synthesis method to develop a singing synthesis system |
| Sub Title (in English) | |
| Keyword(1) | Voice analysis |
| Keyword(2) | Spectral envelope |
| Keyword(3) | Singing voice synthesis |
| Keyword(4) | Pitch synchronous analysis |
| 1st Author's Name | Masanori MORISE |
| 1st Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University() |
| 2nd Author's Name | Kota NAKANO |
| 2nd Author's Affiliation | Graduate School of Science and Engineering, Ritsumeikan University |
| 3rd Author's Name | Takanobu NISHIURA |
| 3rd Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University |
| Date | 2010-06-11 |
| Paper # | EA2010-37 |
| Volume (vol) | vol.110 |
| Number (no) | 71 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |