| Presentation | 2006/8/23 Quality Improvements of Small Body Transmitted Ordinary Speech with Statistical Voice Conversion Hidehiko SEKIMOTO, Tomoki TODA, Hiroshi SARUWATARI, Kiyohiro SHIKANO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The explosive spread of cellular phones enables us to communicate with each other at any time or place. Although cellular phones are convenient, there are still some problems. For example, it is difficult to send intelligible speech under noisy conditions, which is a fatal problem especially when talking privately using small speech in crowds. To improve the quality of small speech under such situations, we propose a new speech communication style using a Non-Audible Murmur (NAM) microphone. The NAM microphone is robust to eternal noise, although body transmission causes quality degradation. To improve the sound quality of Small Body Transmitted Ordinary Speech (SBTOS), which is small speech recorded with a NAM microphone, we propose two conversion methods that reflect a statistical voice conversion method based on Gaussian Mixture Model (GMM). One conversion method is from SBTOS to ordinary speech (SBTOS-to-SP), and the other is from SBTOS to small speech (SBTOS-to-SSP). SBTOS-to-SSP has more consistent correspondence of voiced/unvoiced segments between input and output speech than SBTOS-to-SP. The results of objective and subjective evaluations show that SBTOS-to-SSP outperforms SBTOS-to-SP. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | NAM microphone / voice conversion / small body transmitted ordinary speech / quality improvements / voiced/unvoiced segments |
| Paper # | SP2006-41 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2006/8/23(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) | Quality Improvements of Small Body Transmitted Ordinary Speech with Statistical Voice Conversion |
| Sub Title (in English) | |
| Keyword(1) | NAM microphone |
| Keyword(2) | voice conversion |
| Keyword(3) | small body transmitted ordinary speech |
| Keyword(4) | quality improvements |
| Keyword(5) | voiced/unvoiced segments |
| 1st Author's Name | Hidehiko SEKIMOTO |
| 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 | Hiroshi SARUWATARI |
| 3rd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 4th Author's Name | Kiyohiro SHIKANO |
| 4th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| Date | 2006/8/23 |
| Paper # | SP2006-41 |
| Volume (vol) | vol.106 |
| Number (no) | 221 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |