Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement

TL;DR

This paper introduces a phase continuity loss for neural speech enhancement that leverages phase derivatives across time and frequency, leading to improved speech quality in noisy environments.

Contribution

It proposes a novel phase continuity loss based on phase derivatives, enhancing neural speech enhancement performance beyond existing methods.

Findings

Improved speech quality with phase continuity loss

Effective in noisy environments

Enhancement performance surpasses baseline models

Abstract

Modern neural speech enhancement models usually include various forms of phase information in their training loss terms, either explicitly or implicitly. However, these loss terms are typically designed to reduce the distortion of phase spectrum values at specific frequencies, which ensures they do not significantly affect the quality of the enhanced speech. In this paper, we propose an effective phase reconstruction strategy for neural speech enhancement that can operate in noisy environments. Specifically, we introduce a phase continuity loss that considers relative phase variations across the time and frequency axes. By including this phase continuity loss in a state-of-the-art neural speech enhancement system trained with reconstruction loss and a number of magnitude spectral losses, we show that our proposed method further improves the quality of enhanced speech signals over the baseline, especially when training is done jointly with a magnitude spectrum loss.