Gradient weighting for speaker verification in extremely low Signal-to-Noise Ratio
CoRR(2024)
摘要
Speaker verification is hampered by background noise, particularly at
extremely low Signal-to-Noise Ratio (SNR) under 0 dB. It is difficult to
suppress noise without introducing unwanted artifacts, which adversely affects
speaker verification. We proposed the mechanism called Gradient Weighting
(Grad-W), which dynamically identifies and reduces artifact noise during
prediction. The mechanism is based on the property that the gradient indicates
which parts of the input the model is paying attention to. Specifically, when
the speaker network focuses on a region in the denoised utterance but not on
the clean counterpart, we consider it artifact noise and assign higher weights
for this region during optimization of enhancement. We validate it by training
an enhancement model and testing the enhanced utterance on speaker
verification. The experimental results show that our approach effectively
reduces artifact noise, improving speaker verification across various SNR
levels.
更多查看译文
关键词
Speaker verification,noise-robust,gradient,artificial noise,low SNR
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要