VoiceID Loss: Speech Enhancement for Speaker Verification

2019/04/07 by Suwon Shon, Hao Tang, Shon, Suwon +3 · 7 citations
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #cs.SD #eess.AS #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1904.03601

interspeech 2019; demo link : https://people.csail.mit.edu/swshon/supplement/voiceid-loss

arxiv created 2019/07/05 · arxiv updated 2019/07/08

Abstract

In this paper, we propose VoiceID loss, a novel loss function for training a speech enhancement model to improve the robustness of speaker verification. In contrast to the commonly used loss functions for speech enhancement such as the L2 loss, the VoiceID loss is based on the feedback from a speaker verification model to generate a ratio mask. The generated ratio mask is multiplied pointwise with the original spectrogram to filter out unnecessary components for speaker verification. In the experiments, we observed that the enhancement network, after training with the VoiceID loss, is able to ignore a substantial amount of time-frequency bins, such as those dominated by noise, for verification. The resulting model consistently improves the speaker verification system on both clean and noisy conditions.

Cited by

• Noise-Conditioned Mixture-of-Experts Framework for Robust Speaker Verification
• A Stage-Wise Learning Strategy with Fixed Anchors for Robust Speaker Verification
• DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction
• A Framework for Robust Speaker Verification in Highly Noisy Environments Leveraging Both Noisy and Enhanced Audio
• ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction
• Generic Speech Enhancement with Self-Supervised Representation Space Loss
• Amplifying Artifacts with Speech Enhancement in Voice Anti-spoofing

Related

• Generalized End-to-End Loss for Speaker Verification
• Feature Enhancement with Deep Feature Losses for Speaker Verification
• Analysis of Deep Feature Loss based Enhancement for Speaker Verification
• Unsupervised Feature Enhancement for speaker verification
• Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction