Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P1.8 |
| Session: | Speech Coding for Networks / Single-Channel Speech Enhancement |
| Time: | Tuesday, May 18, 13:00 - 15:00 |
| Presentation: |
Poster |
| Topic: |
Speech Processing: Speech Enhancement |
| Title: |
ON THE DECISION-DIRECTED ESTIMATION APPROACH OF EPHRAIM AND MALAH |
| Authors: |
Israel Cohen; Technion-Israel Institute of Technology | | |
| Abstract: |
The decision-directed approach of Ephraim and Malah is widely used for a priori SNR estimation and speech enhancement. However, it conflicts with common model assumptions. In this paper, we propose consistent recursive estimators for the a priori SNR and the speech spectral components. We introduce a novel statistical model that takes into account the time-correlation between successive speech spectral components, while keeping the resulting algorithms simple. This model provides new insight into the decision-directed approach, and enables the extension of existing speech enhancement algorithms to noncausal estimation. The causal a priori SNR estimator degenerates, as a special case, to a ''decision-directed'' estimator with a \emph{time-varying} weighting factor. The noncausal estimator is capable of discriminating between speech onsets and noise irregularities, achieving lower levels of both musical noise and speech distortion. |
| |
| Back | |