Deep Clustering-Based Single-Channel Speech Separation And Recent Advances
ACOUSTICAL SCIENCE AND TECHNOLOGY(2020)
摘要
The recently-proposed deep clustering algorithm introduced significant advances in single-channel speaker-independent multi-speaker speech separation. In this paper, we review deep clustering and its improved method called chimera net. In addition, we describe our architectures for reducing the latency of deep clustering by combining block processing and teacher-student learning. Unfolding of a phase reconstruction algorithm and a complex mask estimation method for speech separation are also described.
更多查看译文
关键词
Cocktail party problem, Speaker-independent speech separation, Chimera network, Low-latency, Phase estimation
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