Name
Abstract | ||
|---|---|---|
Bayesian estimators of short time spectral amplitude (STSA) have received considerable attention in the field of speech enhancement. In this paper, we propose new multi-microphone extensions for the conventional Ephraim and Malah's speech spectral amplitude estimation method. Unlike the conventional estimators where the spectral phase is assumed to be uniformly distributed, the proposed extensions treat the latter as an unknown parameter to be estimated. It is shown that the proposed methods can exploit spectral phase estimates to improve the performance of the current speech STSA estimators and have the potential to provide even further improvement given a more accurate estimate of the spectral phase. Experimental results indicate the superiority of the new approaches in terms of noise reduction and speech distortion measures, in addition to the reduced computational complexity provided by the proposed minimum mean square method as compared to state-of-the-art solutions. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ISCAS.2014.6865083 | Circuits and Systems |
Keywords | Field | DocType |
Bayes methods,computational complexity,mean square error methods,microphone arrays,natural language processing,speech enhancement,Bayesian estimators,Ephraim speech spectral amplitude estimation method,Malah speech spectral amplitude estimation method,STSA,computational complexity,microphone array,minimum mean square method,multimicrophone extensions,noise reduction,phase estimation,short time spectral amplitude,speech distortion,speech enhancement,speech spectral amplitude estimators,Bayesian STSA estimators,noise reduction,short-time spectral amplitude,speech enhancement | Pattern recognition,Computer science,Microphone array,Speech recognition,Artificial intelligence,Amplitude,Linear predictive coding,Estimator | Conference |
ISSN | Citations | PageRank |
0271-4302 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mahdi Parchami | 1 | 5 | 2.77 |
| Wei-Ping Zhu | 2 | 555 | 62.46 |
| B. Champagne | 3 | 542 | 74.73 |