Single-Microphone Audio Point Source Discriminative Localization From Reverberation Late Tail Estimation

TL;DR

This paper introduces a method to estimate whether two audio signals originate from the same location using late-tail reverberation features and probabilistic modeling, enhancing speaker diarization accuracy.

Contribution

It leverages late-tail reverberation estimation via WPE dereverberation within a probabilistic framework for single-microphone source localization.

Findings

Effective in simulated environments for source discrimination.

Improves speaker diarization accuracy in real room recordings.

Utilizes room-invariant reverberation features for localization.

Abstract

Location information can be a valuable signal for audio segmentation tasks, especially as a complement to methods focusing on the content or qualities of the sources. Though audio source localization is typically performed using the observations of the signal captured by multiple microphones in space, information about a source's location is captured by a single microphone through its arrival time and spectral amplitude--given the source's emitted signal is known. Since reverberation originates from the audio sources in a room, it accordingly contains some information about the emitted audio signals. The late-tail part of reverberation is relatively invariant to the local source and microphone geometry, depending primarily on only the room itself, and thus can provide the necessary reference information about audio signals that depends minimally on their location. In this work, we leverage the robust late-tail estimation of Weighted Prediction Error (WPE) dereverberation within a probabilistic framework to estimate the likelihood of two audio signals collected in the same room as having originated from the same location. We demonstrate the effectiveness of our approach on the speaker diarization task in both simulated and real environments.