| Presentation | 2007/7/19 A Speech Enhancement Framework Based on Noise Eigenspace Projection Dongwen YING, Masashi UNOKI, Jianwu DANG, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The performance of most speech enhancement algorithms declines under low-SNR conditions because of residual noise (or speech distortion) and the degradation of voice activity detector (VAD) performance. We therefore propose a speech enhancement approach based on noise eigenspace projection. When noisy speech is projected into the noise eigenspace, the noise energy is packed to a subspace consisting of dimensions with larger eigenvalues. This subspace is fairly dominated by noise. Removing the noise subspace can greatly reduce the noise at the cost of little speech loss. At the same time, the eigenspace dimensions having little noise are used to make a robust VAD. Using the proposed algorithm as a pre-processing block for conventional enhancement algorithms can efficiently reduce the residual noise under low-SNR conditions. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech enhancement / noise eigenspace / voice activity detection / Karhunen-Loeve transform |
| Paper # | SP2007-42 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2007/7/19(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 | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Speech Enhancement Framework Based on Noise Eigenspace Projection |
| Sub Title (in English) | |
| Keyword(1) | speech enhancement |
| Keyword(2) | noise eigenspace |
| Keyword(3) | voice activity detection |
| Keyword(4) | Karhunen-Loeve transform |
| 1st Author's Name | Dongwen YING |
| 1st Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology() |
| 2nd Author's Name | Masashi UNOKI |
| 2nd Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology |
| 3rd Author's Name | Jianwu DANG |
| 3rd Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology |
| Date | 2007/7/19 |
| Paper # | SP2007-42 |
| Volume (vol) | vol.107 |
| Number (no) | 165 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |