Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

TL;DR

This paper introduces a novel diffusion model-based approach for monaural speech enhancement that separately estimates magnitude and phase spectra, leveraging their intrinsic relationship for improved performance.

Contribution

The paper proposes a complex-cycle-consistent diffusion model that jointly estimates speech magnitude and phase, enhancing speech quality over traditional methods.

Findings

Outperforms conventional diffusion models in speech enhancement tasks

Effectively leverages the relationship between magnitude and phase spectra

Demonstrates significant improvements on public datasets

Abstract

In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion process, noise clips from real-world noise interferences are added gradually to the clean speech spectra and a noise-aware reverse process is proposed to learn how to generate both clean speech spectra and noise spectra. Furthermore, to fully leverage the intrinsic relationship between magnitude and phase, we introduce a complex-cycle-consistent (CCC) mechanism that uses the estimated magnitude to map the phase, and vice versa. We implement this algorithm within a phase-aware speech enhancement diffusion model (SEDM). We conduct extensive experiments on public datasets to demonstrate the effectiveness of our method, highlighting the significant benefits of exploiting the intrinsic relationship between phase and magnitude information to enhance speech. The comparison to conventional diffusion models demonstrates the superiority of SEDM.