The Cone of Silence: Speech Separation by Localization

Part of Advances in Neural Information Processing Systems 33 (NeurIPS 2020)

AuthorFeedback Bibtex MetaReview Paper Review Supplemental

Authors

Teerapat Jenrungrot, Vivek Jayaram, Steve Seitz, Ira Kemelmacher-Shlizerman

Abstract

Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers. At the core of our method is a deep network, in the waveform domain, which isolates sources within an angular region $\theta \pm w/2$, given an angle of interest $\theta$ and angular window size $w$. By exponentially decreasing $w$, we can perform a binary search to localize and separate all sources in logarithmic time. Our algorithm also allows for an arbitrary number of potentially moving speakers at test time, including more speakers than seen during training. Experiments demonstrate state of the art performance for both source separation and source localization, particularly in high levels of background noise.