Abstract
This paper proposes an online single-channel speech enhancement method designed to improve the quality of speech degraded by reverberation and noise. Based on an autoregressive model for the reverberation power and on a hidden Markov model for clean speech production, a Bayesian filtering formulation of the problem is derived and online joint estimation of the acoustic parameters and mean speech, reverberation, and noise powers is obtained in mel-frequency bands. From these estimates, a real-valued spectral gain is derived and spectral enhancement is applied in the short-time Fourier transform (STFT) domain. The method yields state-of-the-art performance and greatly reduces the effects of reverberation and noise while improving speech quality and preserving speech intelligibility in challenging acoustic environments.
Original language | English |
---|---|
Article number | 7795155 |
Journal | I E E E Transactions on Audio, Speech and Language Processing |
Volume | 25 |
Issue number | 3 |
Pages (from-to) | 572-587 |
Number of pages | 16 |
ISSN | 1558-7916 |
DOIs | |
Publication status | Published - 1 Mar 2017 |
Keywords
- Bayesian
- Dereverberation
- Single-Channel
- speech