Subband-Based Blind Signal Processing for Source Separation in Convolutive Mixtures of Speech

This paper describes a highly practical blind signal separation (BSS) scheme operating on subband domain data to blindly segregate convolutive mixtures of speech. The proposed method relies on spatiotemporal separation carried out in the time domain by using a multichannel blind deconvolution (MBD) algorithm that enforces separation by entropy maximization through the popular natural gradient algorithm (NGA). Numerical experiments with binaural impulse responses affirm the validity and illustrate the practical appeal of the presented technique even for difficult speech separation setups.

[1]  R. Lambert.  Multichannel blind deconvolution: FIR matrix algebra and separation of multipath mixtures , 1996 .

[2]  Andrzej Cichocki,et al.  A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[3]  Yunxin Zhao,et al.  Subband-based adaptive decorrelation filtering for co-channel speech separation , 2000, IEEE Trans. Speech Audio Process..

[4]  Shoko Araki,et al.  The fundamental limitation of frequency domain blind source separation for convolutive mixtures of speech , 2003, IEEE Trans. Speech Audio Process..

[5]  P. Vaidyanathan.  Multirate Systems And Filter Banks , 1992 .

[6]  Paris Smaragdis,et al.  Blind separation of convolved mixtures in the frequency domain , 1998, Neurocomputing.

[7]  Barbara G Shinn-Cunningham,et al.  Localizing nearby sound sources in a classroom: binaural room impulse responses. , 2005, The Journal of the Acoustical Society of America.

[8]  Asoke K. Nandi,et al.  Optimal blind separation of convolutive audio mixtures without temporal constraints , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Eric A. Lehmann,et al.  Fast convolutive blind speech separation via subband adaptation , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[10]  Sang-Hoon Oh,et al.  A uniform oversampled filter bank approach to independent component analysis , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[11]  Sven Nordholm,et al.  Blind signal separation using overcomplete subband representation , 2001, IEEE Trans. Speech Audio Process..

[12]  Mark J. T. Smith,et al.  Time-domain filter bank analysis: a new design theory , 1992, IEEE Trans. Signal Process..

[13]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[14]  Asoke K. Nandi,et al.  Exponent parameter estimation for generalized Gaussian probability density functions with application to speech modeling , 2005, Signal Process..

[15]  Lucas C. Parra,et al.  On-line Convolutive Blind Source Separation of Non-Stationary Signals , 2000, J. VLSI Signal Process..

[16]  Asoke K. Nandi,et al.  Multichannel blind deconvolution for source separation in convolutive mixtures of speech , 2006, IEEE Transactions on Audio, Speech, and Language Processing.