A nonlocally weighted soft-constrained natural gradient algorithm and blind separation of strongly reverberant speech mixtures

Authors:
Meng Yu;Jack Xin;Yingyong Qi;Hsin-I Yang;Fan-Gang Zeng
Affiliations:
Department of Mathematics, University of California, Irvine, CA;Department of Mathematics, University of California, Irvine, CA;Department of Mathematics, University of California, Irvine, CA;Department of Biomedical Engineering, University of California, Irvine, CA;Department of Biomedical Engineering, University of California, Irvine, CA
Venue:
Asilomar'09 Proceedings of the 43rd Asilomar conference on Signals, systems and computers
Year:
2009

Citing 3
Cited 0

A dynamic algorithm for blind separation of convolutive sound mixtures

Neurocomputing
A two-stage algorithm for one-microphone reverberant speech enhancement

IEEE Transactions on Audio, Speech, and Language Processing
Spatio–Temporal FastICA Algorithms for the Blind Separation of Convolutive Mixtures

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A nonlocally weighted soft-constrained natural gradient iterative method is introduced for robust blind separation in reverberant environment. The scaling degree of freedom is controled by soft-constraints built into the auxillary difference equations. The small divisor problem of iterations in silence durations of speech is resolved. Computations on synthetic speech mixtures based on measured binaural room impulse responses show that the algorithm achieves consistently higher signal-to-interference ratio improvement (SIRI) than existing methods in enclosed rooms with reverberation time up to 1 second. At 1 second reverberation time, 5 decibel (dB) SIRI is achieved; while with the help of a spectral subtraction dereverberation technique for preprocessing, 9 dB of SIRI is obtained.