An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement

TL;DR

This paper introduces a novel loss function for phase reconstruction and speech enhancement that enforces consistency between magnitude and phase, avoiding direct phase estimation and improving performance.

Contribution

The paper proposes a new consistency-preserving loss function that directly generates a consistent magnitude-phase pair, enhancing phase reconstruction and speech enhancement methods.

Findings

Viability demonstrated on phase reconstruction task

Competitive results on VB-DMD dataset

Favorable comparison on WSJ0-CHiME3 dataset

Abstract

In this work, we propose a novel consistency-preserving loss function for recovering the phase information in the context of phase reconstruction (PR) and speech enhancement (SE). Different from conventional techniques that directly estimate the phase using a deep model, our idea is to exploit ad-hoc constraints to directly generate a consistent pair of magnitude and phase. Specifically, the proposed loss forces a set of complex numbers to be a consistent short-time Fourier transform (STFT) representation, i.e., to be the spectrogram of a real signal. Our approach thus avoids the difficulty of estimating the original phase, which is highly unstructured and sensitive to time shift. The influence of our proposed loss is first assessed on a PR task, experimentally demonstrating that our approach is viable. Next, we show its effectiveness on an SE task, using both the VB-DMD and WSJ0-CHiME3 data sets. On VB-DMD, our approach is competitive with conventional solutions. On the challenging WSJ0-CHiME3 set, the proposed framework compares favourably over those techniques that explicitly estimate the phase.