| Presentation | 2012-11-08 Implementation of real-time statistical voice conversion on a DSP Takuto MORIGUCHI, Tomoki TODA, Motoaki SANO, Hiroshi SANO, Graham NEUBIG, Sakriani SAKTI, Satoshi NAKAMURA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Real-time statistical voice conversion is one of promising approach to developing technology for bodyconducted speech in silent speech communication and alaryngeal speech produced by alternative speaking methods for laryngectomees. Although it has been successfully implemented on devices with sufficient computational resources such as laptop PCs, an implementation in enviromments with limited resources such as portable devices would greatly contribute its practical use. In this report, we implement real-time voice conversion from non-audible murmur into whisper on a DSP for silent speech interfaces. To achieve real-time processing, we propose some methods for reducing computational cost while keeping conversion accuracy high. We conduct an experimental evaluations, which shows effectiveness of the proposed methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | statistical voice conversion / non-audible murmur / real-time processing / DSP / reduction of computational cost |
| Paper # | SP2012-73 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2012/11/1(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) | Implementation of real-time statistical voice conversion on a DSP |
| Sub Title (in English) | |
| Keyword(1) | statistical voice conversion |
| Keyword(2) | non-audible murmur |
| Keyword(3) | real-time processing |
| Keyword(4) | DSP |
| Keyword(5) | reduction of computational cost |
| 1st Author's Name | Takuto MORIGUCHI |
| 1st Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology() |
| 2nd Author's Name | Tomoki TODA |
| 2nd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 3rd Author's Name | Motoaki SANO |
| 3rd Author's Affiliation | Foster Electric Company, Limited |
| 4th Author's Name | Hiroshi SANO |
| 4th Author's Affiliation | Foster Electric Company, Limited |
| 5th Author's Name | Graham NEUBIG |
| 5th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 6th Author's Name | Sakriani SAKTI |
| 6th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 7th Author's Name | Satoshi NAKAMURA |
| 7th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| Date | 2012-11-08 |
| Paper # | SP2012-73 |
| Volume (vol) | vol.112 |
| Number (no) | 281 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |