Speech Denoising in the Waveform Domain with Self-Attention

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. We release our code and models at https://github.com/nvidia/cleanunet.

Published in ICASSP 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Listen to audio samples from CleanUNet at: https://cleanunet.github.io/