SRTNET: Time Domain Speech Enhancement via Stochastic Refinement
Zhibin Qiu, Mengfan Fu, Yinfeng Yu, Lili Yin, Fuchun Sun, Hao Huang
Abstract
Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose SRTNet, a novel method for speech enhancement via Stochastic Refinement in complete Time b domain. Specifically, we design a joint network consisting of a deterministic module and a stochastic module, which makes up the "enhance-and-refine" paradigm. We theoretically demonstrate the feasibility of our method and experimentally prove that our method achieves faster training, faster sampling and higher quality. Our code is available at https://github.com/zhibinQiu/SRTNet.git
BibTeX
@inproceedings{icassp2023_srtnettimedomain,
title = {SRTNET: Time Domain Speech Enhancement via Stochastic Refinement},
author = {Zhibin Qiu and Mengfan Fu and Yinfeng Yu and Lili Yin and Fuchun Sun and Hao Huang},
booktitle = {ICASSP 2023},
year = {2023}
}