A Maximum Likelihood Estimation of Vocal-Tract-Related Filter Characteristics for Single Channel Speech Separation

• Main Authors: Dansereau Richard M, Radfar Mohammad H, Sayadiyan Abolghasem
• Format: Article
• Language: English
• Published: SpringerOpen 2007-01-01
• Series: EURASIP Journal on Audio, Speech, and Music Processing
• Online Access: http://asmp.eurasipjournals.com/content/2007/084186

<p/> <p>We present a new technique for separating two speech signals from a single recording. The proposed method bridges the gap between <it>underdetermined blind source separation</it> techniques and those techniques that model the human auditory system, that is, <it>computational auditory scene analysis</it> (CASA). For this purpose, we decompose the speech signal into the excitation signal and the vocal-tract-related filter and then estimate the components from the mixed speech using a hybrid model. We first express the probability density function (PDF) of the mixed speech's log spectral vectors in terms of the PDFs of the underlying speech signal's vocal-tract-related filters. Then, the mean vectors of PDFs of the vocal-tract-related filters are obtained using a <it>maximum likelihood</it> estimator given the mixed signal. Finally, the estimated vocal-tract-related filters along with the extracted fundamental frequencies are used to reconstruct estimates of the individual speech signals. The proposed technique effectively adds vocal-tract-related filter characteristics as a new cue to CASA models using a new grouping technique based on an underdetermined blind source separation. We compare our model with both an underdetermined blind source separation and a CASA method. The experimental results show that our model outperforms both techniques in terms of SNR improvement and the percentage of crosstalk suppression.</p>