Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net

TL;DR

This paper introduces a single-stage deep learning framework for simultaneous speech denoising and dereverberation, utilizing a novel phase-aware masking technique, a new loss function, and optimized U-Net architecture for real-time processing.

Contribution

It proposes a unified single-stage network with a phase-aware mask, a new time-domain loss, and an optimized U-Net for real-time speech enhancement.

Findings

The phase-aware beta-sigmoid mask effectively estimates clean phase.

The new loss function improves speech enhancement performance.

The optimized U-Net reduces computational overhead by up to 88.9%.

Abstract

In this work, we tackle a denoising and dereverberation problem with a single-stage framework. Although denoising and dereverberation may be considered two separate challenging tasks, and thus, two modules are typically required for each task, we show that a single deep network can be shared to solve the two problems. To this end, we propose a new masking method called phase-aware beta-sigmoid mask (PHM), which reuses the estimated magnitude values to estimate the clean phase by respecting the triangle inequality in the complex domain between three signal components such as mixture, source and the rest. Two PHMs are used to deal with direct and reverberant source, which allows controlling the proportion of reverberation in the enhanced speech at inference time. In addition, to improve the speech enhancement performance, we propose a new time-domain loss function and show a reasonable performance gain compared to MSE loss in the complex domain. Finally, to achieve a real-time inference, an optimization strategy for U-Net is proposed which significantly reduces the computational overhead up to 88.9% compared to the na\"ive version.