13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Constrained Multichannel Speech Dereverberation

Meng Yu (1), Frank K. Soong (2)

(1) Department of Mathematics, University of California, Irvine, USA
(2) Microsoft Research Asia, Beijing, China

We propose a multi-channel speech dereverberation approach based on cross-channel cancellation and spectrogram decomposition. The reverberation is modeled as a convolution operation in the spectrogram magnitude domain. Using the Itakura divergence (I-divergence), we decompose reverberant spectrogram into clean spectrogram convolved with a deconvolution filter. The speech spectrogram is constrained and regularized by non-negativity and sparsity, respectively, while the deconvolution filter is constrained by non-negativity and cross-channel cancellation. Spectrogram decomposition of individual channels and cross-channel cancellation are jointly optimized by a multiplicative algorithm to achieve multi-channel speech dereverberation. We confirm through experiment that the proposed multi-channel method outperforms the related other single/multi-channel methods.

Index Terms: Multichannel dereverberation, Spectral decomposition, I-divergence, Sparsity, Cross-channel cancellation

Full Paper

Audio Examples

Experiment 1: Demo of the Proposed Method
200 ms   Reverberant    Processed   
400 ms   Reverberant    Processed   
600 ms   Reverberant    Processed   
800 ms   Reverberant    Processed   
room      Reverberant    Processed   

Experiment 2: Comparison (see explanation)
Reverberant     (a)   (b)   (c)   (d)   (e)   (f)   (g)  

Bibliographic reference.  Yu, Meng / Soong, Frank K. (2012): "Constrained multichannel speech dereverberation", In INTERSPEECH-2012, 1938-1941.