Speech Enhancement with Fullband-Subband Cross-Attention Network

Conference of the International Speech Communication Association (INTERSPEECH)(2022)

引用 1|浏览6
暂无评分
摘要
FullSubNet has shown its promising performance on speech enhancement by utilizing both fullband and subband information. However, the relationship between fullband and subband in FullSubNet is achieved by simply concatenating the output of fullband model and subband units. It only supplements the subband units with a small quantity of global information and has not considered the interaction between fullband and subband. This paper proposes a fullband-subband cross-attention (FSCA) module to interactively fuse the global and local information and applies it to FullSubNet. This new framework is called as FS-CANet. Moreover, different from FullSubNet, the proposed FS-CANet optimize the fullband extractor by temporal convolutional network (TCN) blocks to further reduce the model size. Experimental results on DNS Challenge - Interspeech 2021 dataset show that the proposed FS-CANet outperforms other state-of-the-art speech enhancement approaches, and demonstrate the effectiveness of fullband-subband cross-attention.
更多
查看译文
关键词
speech enhancement,fullband-subband,cross-attention
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