Stabilizing Label Assignment for Speech Separation by Self-Supervised Pre-Training.
Interspeech(2021)
摘要
Speech separation has been well developed, with the very successful permutation invariant training (PIT) approach, although the frequent label assignment switching happening during PIT training remains to be a problem when better convergence speed and achievable performance are desired. In this paper, we propose to perform self-supervised pre-training to stabilize the label assignment in training the speech separation model. Experiments over several types of self-supervised approaches, several typical speech separation models and two different datasets showed that very good improvements are achievable if a proper self-supervised approach is chosen.
更多查看译文
关键词
Speech Enhancement,Self-supervised Pre-train,Speech Separation,Label Permutation Switch
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