SRTNet: Time Domain Speech Enhancement Via Stochastic Refinement

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 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.