| Presentation | 2007/12/13 Noise Suppression Using Multi-noise Model Compositions Integrating Particle Filtering Takatoshi JITSUHIRO, Tomoji TORIYAMA, Kiyoshi KOGURE, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a noise suppression method based on multi-model compositions using particle filtering. In real environments, input speech for speech recognition includes many kinds of noise signals. For such noisy speech, we have proposed Multi-Model Noise Suppression (MM-NS) that uses many kinds of noise models and their compositions obtained from training data. However, MM-NS only uses static property of noise models, and it is difficult to handle unknown noise distributions. We introduce a particle filter into MM-NS. The distributions of noise models is used as prior distributions of particle filtering. It makes more accurate estimation of noise signals for input data. We evaluated this method using the E-Nightingale task, which contains voice memoranda spoken by nurses during actual work at hospitals. The proposed method obtained higher performance than the original MM-NS. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / noise suppression / model composition / particle filter / E-Nightingale project |
| Paper # | NLC2007-66,SP2007-129 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2007/12/13(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) | Noise Suppression Using Multi-noise Model Compositions Integrating Particle Filtering |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | noise suppression |
| Keyword(3) | model composition |
| Keyword(4) | particle filter |
| Keyword(5) | E-Nightingale project |
| 1st Author's Name | Takatoshi JITSUHIRO |
| 1st Author's Affiliation | ATR Knowledge Science Laboratories() |
| 2nd Author's Name | Tomoji TORIYAMA |
| 2nd Author's Affiliation | ATR Knowledge Science Laboratories |
| 3rd Author's Name | Kiyoshi KOGURE |
| 3rd Author's Affiliation | ATR Knowledge Science Laboratories |
| Date | 2007/12/13 |
| Paper # | NLC2007-66,SP2007-129 |
| Volume (vol) | vol.107 |
| Number (no) | 406 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |