Modified Parametric Multichannel Wiener Filter for Low-latency Enhancement of Speech Mixtures with Unknown Number of Speakers

This paper introduces a novel low-latency online beamforming (BF) algorithm called the Modified Parametric Multichannel Wiener Filter (Mod-PMWF), which enhances speech mixtures with unknown and varying number of speakers. Although such conventional BFs as Linearly Constrained Minimum Variance BFs (LCMV BFs) can enhance a speech mixture, they typically require such speech mixture attributes as the number of speakers and the acoustic transfer functions (ATFs) from the speakers to the microphones. When mixture attributes are unavailable, estimating them by low-latency processing is challenging, hindering the application of BFs to the problem. In this paper, we overcome this problem by modifying a conventional Parametric Multichannel Wiener Filter (PMWF). The proposed Mod-PMWF can adaptively form a directivity pattern that enhances all the speakers in the mixture without explicitly estimating these attributes. Our experiments show the proposed BF's effectiveness in interference reduction ratios and subjective listening tests.