Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Joint Speech Signal Enhancement Based on Spectral Subtraction and SVD Filter

Wenkai Lu (1), Xuegong Zhang (1), Yanda Li (1), Shen Liqin (2), Zhu Weibin (2)

(1) Institute of information processing, Department of automation, Key State Lab of Intelligent TechnSystem, Tsinghua University, Beijing, China System, Tsinghua University, Beijing, China
(2) Speech Group, IBM China Research, Shangdi, Haidian District, Beijing, China

A joint speech signal enhancement based on singular value decomposition filter after spectral subtraction (SSVD) is proposed in this paper. The residual noise after spectral subtraction, which results for audible musical noise, is reduced further by SVD filter. The matrix size in spectral domain can be reduced half, and larger step-length adopted by SVD filter in spectral domain leads to lower cost, which make sure that the system can work in real-time. A novel speech/pause detector based on entropy(ESPD) is proposed too. The new detector improves the performance of the whole noise suppression system significantly.

Full Paper

Bibliographic reference.  Lu, Wenkai / Zhang, Xuegong / Li, Yanda / Liqin, Shen / Weibin, Zhu (2000): "Joint speech signal enhancement based on spectral subtraction and SVD filter", In ICSLP-2000, vol.4, 656-659.