Reverberation-Robust Localization of Speakers Using Distinct Speech Onsets and Multi-channel Cross-Correlations

TL;DR

This paper introduces two novel algorithms for localizing speakers in reverberant environments, leveraging speech onsets and multi-microphone correlations to improve accuracy under challenging acoustic conditions.

Contribution

The paper presents new algorithms that enhance speaker localization robustness in reverberant settings by using speech onset detection and multi-channel cross-correlation techniques.

Findings

Algorithms reliably locate static and moving speakers in reverberant rooms.

Proposed methods outperform some state-of-the-art localization techniques.

Effective in both simulated and real reverberant environments.

Abstract

Many speaker localization methods can be found in the literature. However, speaker localization under strong reverberation still remains a major challenge in the real-world applications. This paper proposes two algorithms for localizing speakers using microphone array recordings of reverberated sounds. To separate concurrent speakers, the first algorithm decomposes microphone signals spectrotemporally into subbands via an auditory filterbank. To suppress reverberation, we propose a novel speech onset detection approach derived from the speech signal and impulse response models, and further propose to formulate the multi-channel cross-correlation coefficient (MCCC) of encoded speech onsets in each subband. The subband results are combined to estimate the directions-of-arrival (DOAs) of speakers. The second algorithm extends the generalized cross-correlation - phase transform (GCC-PHAT) method by using redundant information of multiple microphones to address the reverberation problem. The proposed methods have been evaluated under adverse conditions using not only simulated signals (reverberation time $T_{60}$ of up to $1$s) but also recordings in a real reverberant room ($T_{60} \approx 0.65$s). Comparing with some state-of-the-art localization methods, experimental results confirm that the proposed methods can reliably locate static and moving speakers, in presence of reverberation.