Skip to Main content Skip to Navigation
Conference papers

Phase recovery with Bregman divergences for audio source separation

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.
Complete list of metadata
Contributor : Paul Magron Connect in order to contact the contributor
Submitted on : Tuesday, February 9, 2021 - 4:53:43 PM
Last modification on : Tuesday, November 16, 2021 - 4:34:25 PM


Files produced by the author(s)


  • HAL Id : hal-03049800, version 2
  • ARXIV : 2010.10255


Paul Magron, Pierre-Hugo Vial, Thomas Oberlin, Cédric Févotte. Phase recovery with Bregman divergences for audio source separation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, Canada. ⟨hal-03049800v2⟩



Record views


Files downloads