Hybrid Source Prior Based Independent Vector Analysis for Blind Separation of Speech Signals

• Published in: IEEE access 2020, Vol.8, p.132871-132881
• Main Authors: Khan, Junaid Bahadar, Jan, Tariqullah, Khalil, Ruhul Amin, Altalbe, Ali
• Format: Article
• Language: English
• Subjects: Blind source separation; Blind source separation (BSS); convolutive speech mixture; Correlation; Frequency-domain analysis; Gaussian distribution; Independent component analysis; independent vector analysis; Multivariate analysis; Normal distribution; Permutations; Probability density function; Separation; Signal processing; Speech; Speech processing; Statistical analysis; Time-domain analysis; Vector analysis
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.3010342

Blind Source Separation (BSS) application is a delinquent issue in a complex reverberant environment with changing room geometric dimensions and an increasing number of speech sources. The BSS application issue is determined by the independent component analysis that usually manipulates higher-order statistical approaches. However, the permutation between desired speech sources remains a challenging issue for BSS applications. The permutation problem is been rectified by Independent Vector Analysis (IVA) for BSS applications in the frequency domain. The performance dependency of the IVA approach solely relies on the selection of appropriate source-prior to preserve the inter-frequency dependencies between the same speech source amongst different frequency bins. Therefore, a hybrid model for the IVA method is presented, which comprises of multivariate generalized Gaussian and super-Gaussian distribution source priors to model low as well as high amplitudes speech signals. The weights of the hybrid model between multivariate Gaussian and generalized Gaussian are assigned in accordance to the energy of the observed non-stationary speech mixture signal. In the simulations, different speech mixtures are generated from various speech sources by simulated room model. The proposed approach evaluates the blind separation performance in terms of signal-to-distortion ratio (SDR) and is compared with well-known BSS methods. The results show an improvement of the proposed methodology for non-stationary speech signals over the state-of-the-art IVA models having a fixed source prior.