Speech Denoising in the Waveform Domain With Self-Attention

Zhifeng Kong; Wei Ping; Ambrish Dantrey; Bryan Catanzaro

ICASSP 2022accepted0 citations

Speech Denoising in the Waveform Domain With Self-Attention

Zhifeng Kong, Wei Ping, Ambrish Dantrey, Bryan Catanzaro

Abstract

In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations, which is crucial to obtain good results. The model is optimized through a set of losses defined over both waveform and multi-resolution spectrograms. The proposed method outperforms the state-of-the-art models in terms of denoised speech quality from various objective and subjective evaluation metrics. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

BibTeX

@inproceedings{icassp2022_speechdenoisingi,
  title = {Speech Denoising in the Waveform Domain With Self-Attention},
  author = {Zhifeng Kong and Wei Ping and Ambrish Dantrey and Bryan Catanzaro},
  booktitle = {ICASSP 2022},
  year = {2022}
}