Localisation-based, situation-adaptive mask generation for source separation

Presented is a microphone-array based approach for the extraction of individual signals from a mixture of competing sources and background noise. Source separation is done using data-driven soft-masks, the parameters for the estimation of these masks being obtained from an extension of a recently proposed source localisation and tracking framework. The separation algorithm is applicable to any arbitrary array - allowing for its integration into a wide variety of applications. The advantage of the proposed mask generation over state-of-the-art mask-based algorithms is the implicit scalability with respect to the number of microphones (M), the number of sources (Q), spatial source spread, and reverberation - obviating the need for heuristic adaptation of the mask generation to different acoustical scenarios. The individual signals extracted using the soft-masks evince low amounts of musical noise. Smoothing these masks in their cepstral representation further reduces the musical noise phenomenon whilst preserving the signal of interest, thereby improving the listening experience.