作者
Sung-Feng Huang, Shun-Po Chuang, Da-Rong Liu, Yi-Chen Chen, Gene-Ping Yang, Hung-yi Lee
发表日期
2020/10/29
研讨会论文
Proc. Interspeech 2021
页码范围
3056--3060
简介
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.
学术搜索中的文章
SF Huang, SP Chuang, DR Liu, YC Chen, GP Yang… - arXiv preprint arXiv:2010.15366, 2020
SF Huang, SP Chuang, DR Liu, YC Chen, GP Yang… - arXiv preprint arXiv:2010.15366, 2020