English

Phase recovery with Bregman divergences for audio source separation

Sound 2021-02-10 v2 Audio and Speech Processing

Abstract

Time-frequency audio source separation is usually achieved by estimating the short-time Fourier transform (STFT) magnitude of each source, and then applying a phase recovery algorithm to retrieve time-domain signals. In particular, the multiple input spectrogram inversion (MISI) algorithm has shown good performance in several recent works. This algorithm minimizes a quadratic reconstruction error between magnitude spectrograms. However, this loss does not properly account for some perceptual properties of audio, and alternative discrepancy measures such as beta-divergences have been preferred in many settings. In this paper, we propose to reformulate phase recovery in audio source separation as a minimization problem involving Bregman divergences. To optimize the resulting objective, we derive a projected gradient descent algorithm. Experiments conducted on a speech enhancement task show that this approach outperforms MISI for several alternative losses, which highlights their relevance for audio source separation applications.

Keywords

Cite

@article{arxiv.2010.10255,
  title  = {Phase recovery with Bregman divergences for audio source separation},
  author = {Paul Magron and Pierre-Hugo Vial and Thomas Oberlin and Cédric Févotte},
  journal= {arXiv preprint arXiv:2010.10255},
  year   = {2021}
}
R2 v1 2026-06-23T19:29:15.419Z