AndongLi

icon indicating a website link https://andong-li-speech.github.io icon indicating an email [email protected]

icon location Beijing, China icon location Institute of Acoustics, Chinese Academy of Sciences (IACAS).

Results 2 issues of AndongLi

A Question about causal-convolution operation.

2 comment

Hi, I have a question about causal-convolution in Auto-encoder based CRNN. The author Tan mentioned the usage of causal-convolution in his paper, where only current timestep is involved in convolution...

The range of mask

1 comment

Hi, thanks for your release of the code w.r.t. component loss, it is an interesting work that separates noise suppression and speech reservation respectively. I have a question about the...