Title | ||
---|---|---|
Multichannel Speech Enhancement Based on Speech Spectral Magnitude Estimation Using Generalized Gamma Prior Distribution |
Abstract | ||
---|---|---|
We present multichannel speech enhancement method based on MAP speech spectral magnitude estimation using a generalized gamma model of speech prior distribution, where the model parameters are adapted from actual noisy speech in a frame-by-frame manner. The utilization of a more general prior distribution with its online estimation is shown to be effective for speech spectral estimation. We tested the proposed algorithm in an in-car speech database and obtained significant improvements on the speech recognition performance, particularly under nonstationary noise conditions such as music, air-conditioner and open window |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICASSP.2006.1661177 | Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference |
Keywords | Field | DocType |
gamma distribution,maximum likelihood estimation,speech enhancement,speech recognition,MAP estimation,generalized gamma prior distribution,in-car speech database,multichannel speech enhancement,noisy speech,speech recognition performance,speech spectral magnitude estimation | Speech enhancement,Magnitude (mathematics),Spectral density estimation,Speech coding,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Gamma distribution,Speech recognition performance,Prior probability,Linear predictive coding | Conference |
Volume | ISSN | ISBN |
4 | 1520-6149 | 1-4244-0469-X |
Citations | PageRank | References |
4 | 0.49 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tran Huy Dat | 1 | 165 | 25.31 |
Kazuya Takeda | 2 | 1301 | 195.60 |
Fumitada Itakura | 3 | 431 | 67.73 |