Under-determined reverberant audio source separation using a full-rank spatial covariance model

Ngoc Q. K. Duong (1) , Emmanuel Vincent (1) , Rémi Gribonval (1)

1 METISS - Speech and sound data modeling and processing

This article addresses the modeling of reverberant recording environments in the context of under-determined convolutive blind source separation. We model the contribution of each source to all mixture channels in the time-frequency domain as a zero-mean Gaussian random variable whose covariance encodes the spatial characteristics of the source. We then consider four specific covariance models, including a full-rank unconstrained model. We derive a family of iterative expectationmaximization (EM) algorithms to estimate the parameters of each model and propose suitable procedures to initialize the parameters and to align the order of the estimated sources across all frequency bins based on their estimated directions of arrival (DOA). Experimental results over reverberant synthetic mixtures and live recordings of speech data show the effectiveness of the proposed approach.

Mots clés: permutation problem; Convolutive blind source separation; underdetermined mixtures; spatial covariance models; EM algorithm; permutation problem.

Domaines: Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Ngoc Q. K. Duong, Emmanuel Vincent, Rémi Gribonval. Under-determined reverberant audio source separation using a full-rank spatial covariance model. [Research Report] INRIA. 2010. ⟨inria-00435807v2⟩