Blind Source Separation Combining Independent Component Analysis and Beamforming

Abstract

We describe a new method of blind source separation (BSS) on a microphone array combining subband independent component analysis (ICA) and beamforming. The proposed array system consists of the following three sections: (1) subband ICA-based BSS section with estimation of the direction of arrival (DOA) of the sound source, (2) null beamforming section based on the estimated DOA, and (3) integration of (1) and (2) based on the algorithm diversity. Using this technique, we can resolve the low-convergence problem through optimization in ICA. To evaluate its effectiveness, signal-separation and speech-recognition experiments are performed under various reverberant conditions. The results of the signal-separation experiments reveal that the noise reduction rate (NRR) of about 18 dB is obtained under the nonreverberant condition, and NRRs of 8 dB and 6 dB are obtained in the case that the reverberation times are 150 milliseconds and 300 milliseconds. These performances are superior to those of both simple ICA-based BSS and simple beamforming method. Also, from the speech-recognition experiments, it is evident that the performance of the proposed method in terms of the word recognition rates is superior to those of the conventional ICA-based BSS method under all reverberant conditions

Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

“…There exist more approaches to the ambiguity problems. Saruwatari et al (2003) suggest to use beamforming methods and analyze the directivity patterns determined by the BSS to identify the directions of arrival (DOA) of the sources.…”

Selective Listening Point Audio Based on Blind Signal Separation and Stereophonic Technology

“…In particular, the frequency-domain ICA [10] combined with advanced methods for solving permutation ambiguity [11] is powerful under realistic acoustic conditions. However, since the assumption about the number of sources is crucial in BSS, accurate estimation of the independent source is difficult in such applications as SLP where the number of sound sources varies widely.…”

MLSP 2007 Data Analysis Competition: Frequency-Domain Blind Source Separation for Convolutive Mixtures of Speech/Audio Signals

“…Among them, we consider the frequency-domain approach [6][7][8][9][10][11][12][13][14] where we apply a short-time Fourier transform (STFT) to the sensor observations xj(t). If we use a sufficiently long frame for STFT to cover the main part of the impulse responses h jk , the convolutive mixture (1) can be approximated well with an instantaneous mixture at each frequency f :…”

“…The ambiguities should be aligned properly so that the separated signals that originate from the same source are grouped together. This problem is known as the permutation problem of frequencydomain BSS, and various methods [6][7][8][9][10][11][12][13][14] have been proposed for its solution. Section 4 discusses a strategy that exploits the mutual dependence of bin-wise separated signals across frequencies [8][9][10]14].…”

“…Section 4 discusses a strategy that exploits the mutual dependence of bin-wise separated signals across frequencies [8][9][10]14]. The advantage of this strategy is that it is less affected by bad mixing conditions, such as severe reverberations or closely located sources, than another popular strategy based on time-difference-of-arrival estimations [10,11].…”