Blind speech separation based on undecimated wavelet packet-perceptual filterbanks and independent component analysis
This work addresses the problem of separating mixed speech signals for audio processing applications, but it is incremental as it builds on existing methods like ICA with a new preprocessing step.
The authors tackled blind separation of speech mixtures by integrating a perceptual filterbank with independent component analysis, achieving a considerable improvement over FastICA and other techniques in experiments with two speech sources and two sensors.
In this paper, we address the problem of blind separation of speech mixtures. We propose a new blind speech separation system, which integrates a perceptual filterbank and independent component analysis (ICA) and using kurtosis criterion. The perceptual filterbank was designed by adjusting undecimated wavelet packet decomposition (UWPD) tree in order to accord to critical band characteristics of psycho-acoustic model. Our proposed technique consists on transforming the observations signals into an adequate representation using UWPD and Kurtosis maximization criterion in a new preprocessing step in order to increase the non-Gaussianity which is a pre-requirement for ICA. Experiments were carried out with the instantaneous mixture of two speech sources using two sensors. The obtained results show that the proposed method gives a considerable improvement when compared with FastICA and other techniques.