SVVAD: Personal Voice Activity Detection for Speaker Verification
This addresses the issue of inaccurate VAD in speaker verification systems, particularly in challenging environments, though it appears incremental as it builds on existing VAD methods.
The paper tackled the problem of voice activity detection (VAD) for speaker verification (SV) by proposing SVVAD, a framework that adapts speech features to be more informative for SV, resulting in significant improvements in equal error rate (EER) under noisy and multi-speaker conditions.
Voice activity detection (VAD) improves the performance of speaker verification (SV) by preserving speech segments and attenuating the effects of non-speech. However, this scheme is not ideal: (1) it fails in noisy environments or multi-speaker conversations; (2) it is trained based on inaccurate non-SV sensitive labels. To address this, we propose a speaker verification-based voice activity detection (SVVAD) framework that can adapt the speech features according to which are most informative for SV. To achieve this, we introduce a label-free training method with triplet-like losses that completely avoids the performance degradation of SV due to incorrect labeling. Extensive experiments show that SVVAD significantly outperforms the baseline in terms of equal error rate (EER) under conditions where other speakers are mixed at different ratios. Moreover, the decision boundaries reveal the importance of the different parts of speech, which are largely consistent with human judgments.