Underdetermined Reverberant Blind Source Separation: Sparse Approaches for Multiplicative and Convolutive Narrowband Approximation

Séparation aveugle de source réverbérante: les approches parcimonieuses pour l'approximation multiplicative et convolutive

Fangchen Feng (1) , Matthieu Kowalski (2)

1 APC (UMR_7164) - AstroParticule et Cosmologie
2 L2S - Laboratoire des signaux et systèmes

We consider the problem of blind source separation for underdetermined convolutive mixtures. Based on the multiplicative narrowband approximation in the time-frequency domain with the help of Short-Time-Fourier-Transform (STFT) and the sparse representation of the source signals, we formulate the separation problem into an optimization framework. This framework is then generalized based on the recently investigated convolutive narrowband approximation and the statistics of the room impulse response. Algorithms with convergence proof are then employed to solve the proposed optimization problems. The evaluation of the proposed frameworks and algorithms for synthesized and live recorded mixtures are illustrated. The proposed approaches are also tested for mixtures with input noise. Numerical evaluations show the advantages of the proposed methods.

Mots clés: Sparse regularization; Blind source separation BSS; Room impulse responses; Optimization Algorithms

Domaines: Sciences de l'ingénieur [physics]; Traitement du signal et de l'image [eess.SP]

Fangchen Feng, Matthieu Kowalski. Underdetermined Reverberant Blind Source Separation: Sparse Approaches for Multiplicative and Convolutive Narrowband Approximation. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2019, 27 (2), pp.442-456. ⟨10.1109/taslp.2018.2881925⟩. ⟨hal-01760968⟩