TY - JOUR

T1 - Parametric-Pearson-based independent component analysis for frequency-domain blind speech separation

AU - Kato, Hiroko

AU - Nagahara, Yuichi

AU - Araki, Shoko

AU - Sawada, Hiroshi

AU - Makino, Shoji

PY - 2006

Y1 - 2006

N2 - Separation performance is improved in frequency-domain blind source separation (BSS) of speech with independent component analysis (ICA) by applying a parametric Pear-son distribution system. ICA adaptation rules include a score function determined by approximated source distribution, and better approximation improves separation per-formance. Previously, conventional hyperbolic tangent (tanh) or generalized Gaussian distribution (GGD) was uniformly applied to the score function for all frequency bins, despite the fact that a wideband speech signal has different distributions at different frequencies. To obtain better score functions, we propose the integration of a parametric Pear-son distribution system with ICA learning rules. The score function is estimated by using appropriate Pearson distribu-tion parameters for each frequency bin. We consider three estimation methods with Pearson distribution parameters and conduct separation experiments with real speech sig-nals convolved with actual room impulse responses. Conse-quently, the signal-to-interference ratio (SIR) of the pro-posed methods significantly improve over 3 dB compared to conventional methods.

AB - Separation performance is improved in frequency-domain blind source separation (BSS) of speech with independent component analysis (ICA) by applying a parametric Pear-son distribution system. ICA adaptation rules include a score function determined by approximated source distribution, and better approximation improves separation per-formance. Previously, conventional hyperbolic tangent (tanh) or generalized Gaussian distribution (GGD) was uniformly applied to the score function for all frequency bins, despite the fact that a wideband speech signal has different distributions at different frequencies. To obtain better score functions, we propose the integration of a parametric Pear-son distribution system with ICA learning rules. The score function is estimated by using appropriate Pearson distribu-tion parameters for each frequency bin. We consider three estimation methods with Pearson distribution parameters and conduct separation experiments with real speech sig-nals convolved with actual room impulse responses. Conse-quently, the signal-to-interference ratio (SIR) of the pro-posed methods significantly improve over 3 dB compared to conventional methods.

UR - http://www.scopus.com/inward/record.url?scp=84862597942&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862597942&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84862597942

JO - European Signal Processing Conference

JF - European Signal Processing Conference

SN - 2219-5491

T2 - 14th European Signal Processing Conference, EUSIPCO 2006

Y2 - 4 September 2006 through 8 September 2006

ER -