13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Exploring Off Time Nature for Speech Enhancement

Meng Yu, Jack Xin

Department of Mathematics, University of California, Irvine, CA, USA

It is well known that human conversational speech is “sparse” in time domain, comprising of many “off” time segments. This suggests the utility of the “off” time nature for the task of speech enhancement. We propose an efficient dualmicrophone method based on regularized cross-channel cancellation to distinguish the overlapping and single speech segments in the multi-speaker conversational environment. Fortunately, the regularized cancellation results can be reused for speech enhancement along an interference-suppression chain. We present evaluations of the proposed overlapping speech detection and integrated speech enhancement approaches using an IEEE speech database and real room recordings under various acoustic environments, showing promising improvements for speech enhancement by exploring the off time nature.

Index Terms: Overlapping speech detection, cross-channel cancellation, speech enhancement, l1 optimization.

Full Paper

Audio Examples
Noisy_1     Enhanced_1
Noisy_2     Enhanced_2
Noisy_3     Enhanced_3
Noisy_4     Enhanced_4_1     Enhanced_4_2

Bibliographic reference.  Yu, Meng / Xin, Jack (2012): "Exploring off time nature for speech enhancement", In INTERSPEECH-2012, 150-153.