Multi-Channel Speaker Verification for Single and Multi-talker Speech

TL;DR

This paper enhances speaker verification in challenging environments by integrating multi-channel speech features, speech enhancement, and contrastive learning, resulting in significant error rate reductions especially in multi-talker scenarios.

Contribution

It introduces a multi-channel feature fusion framework combined with supervised learning techniques and contrastive fine-tuning for improved speaker verification performance.

Findings

36% relative EER reduction on real multi-talker recordings

Consistent improvements with speaker-dependent directional features

Additional 8.3% relative EER reduction with contrastive loss fine-tuning

Abstract

To improve speaker verification in real scenarios with interference speakers, noise, and reverberation, we propose to bring together advancements made in multi-channel speech features. Specifically, we combine spectral, spatial, and directional features, which includes inter-channel phase difference, multi-channel sinc convolutions, directional power ratio features, and angle features. To maximally leverage supervised learning, our framework is also equipped with multi-channel speech enhancement and voice activity detection. On all simulated, replayed, and real recordings, we observe large and consistent improvements at various degradation levels. On real recordings of multi-talker speech, we achieve a 36% relative reduction in equal error rate w.r.t. single-channel baseline. We find the improvements from speaker-dependent directional features more consistent in multi-talker conditions than clean. Lastly, we investigate if the learned multi-channel speaker embedding space can be made more discriminative through a contrastive loss-based fine-tuning. With a simple choice of Triplet loss, we observe a further 8.3% relative reduction in EER.