English

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

Audio and Speech Processing 2024-09-25 v1 Sound

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.

Keywords

Cite

@article{arxiv.2409.16282,
  title  = {An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement},
  author = {Pin-Jui Ku and Chun-Wei Ho and Hao Yen and Sabato Marco Siniscalchi and Chin-Hui Lee},
  journal= {arXiv preprint arXiv:2409.16282},
  year   = {2024}
}

Comments

5 pages, Submitted to ICASSP 2025

R2 v1 2026-06-28T18:55:35.826Z