12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

An Assessment of the Improvement Potential of Time-Frequency Masking for Speech Dereverberation

Chenxi Zheng (1), Tiago H. Falk (2), Wai-Yip Chan (1)

(1) Queen's University, Canada
(2) INRS-EMT, Canada

The effect of ideal time-frequency masking (ITFM) on the intelligibility of reverberated speech is tested using objective measurement, namely STI and PESQ scores. The best choice of ITFM threshold is determined for a range of reverberation times (RTs). Four existing dereverberation algorithms are also assessed. Objective test results and informal subjective listening show that IFTM provides great intelligibility improvement for all RTs and outperforms the existing dereverberation algorithms, one of which assumes perfect knowledge of the room impulse response. While ITFM provides only a best possible performance bound, our results demonstrate the potential improvement that could be obtained using time-frequency masking for speech dereverberation.

Full Paper

Bibliographic reference.  Zheng, Chenxi / Falk, Tiago H. / Chan, Wai-Yip (2011): "An assessment of the improvement potential of time-frequency masking for speech dereverberation", In INTERSPEECH-2011, 205-208.