| Presentation | 2008-06-13 A Method for Sudden Noise Reduction from Speech Using a Stationary-Nonstationary Separating Filter Naoki KYOYA, Kaoru ARAKAWA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Authors propose a method for sudden noise reduction. This method first detects noisy part of the input signal, contaminated with sudden noise, using a nonlinear digital filter, named as a stationary-nonstationary separating filter, and then applies time-frequency domain masking only to the noisy parts in order to reduce the noise with minimum distortion. The voice model and the noise model are required to realize the time-frequency domain masking. The voice model is generated from both of training speech data and the part of the input signal, judged as a clean part without noise by the stationary-nonstationary separating filter. The noise model is generated from training noise data. These two models are used to calculate masking function. Computer simulations verify the high performance of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | sudden noise / noise reduction / time-frequency domain masking / speech processing / stationary-nonstationary separating filter |
| Paper # | SIS2008-14 |
| Date of Issue |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2008/6/6(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 | Smart Info-Media Systems (SIS) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Method for Sudden Noise Reduction from Speech Using a Stationary-Nonstationary Separating Filter |
| Sub Title (in English) | |
| Keyword(1) | sudden noise |
| Keyword(2) | noise reduction |
| Keyword(3) | time-frequency domain masking |
| Keyword(4) | speech processing |
| Keyword(5) | stationary-nonstationary separating filter |
| 1st Author's Name | Naoki KYOYA |
| 1st Author's Affiliation | Department of Computer Science, Graduate School of Science and Technology, Meiji University() |
| 2nd Author's Name | Kaoru ARAKAWA |
| 2nd Author's Affiliation | Department of Computer Science, Graduate School of Science and Technology, Meiji University |
| Date | 2008-06-13 |
| Paper # | SIS2008-14 |
| Volume (vol) | vol.108 |
| Number (no) | 86 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |