Model-based STFT phase recovery for audio source separation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Audio, Speech and Language Processing Année : 2018

Model-based STFT phase recovery for audio source separation

Résumé

For audio source separation applications, it is common to estimate the magnitude of the short-time Fourier transform (STFT) of each source. In order to further synthesizing time-domain signals, it is necessary to recover the phase of the corresponding complex-valued STFT. Most authors in this field choose a Wiener-like filtering approach which boils down to using the phase of the original mixture. In this paper, a different standpoint is adopted. Many music events are partially composed of slowly varying sinusoids and the STFT phase increment over time of those frequency components takes a specific form. This allows phase recovery by an unwrapping technique once a short-term frequency estimate has been obtained. Herein, a novel iterative source separation procedure is proposed which builds upon these results. It consists in minimizing the mixing error by means of the auxiliary function method. This procedure is initialized by exploiting the unwrapping technique in order to generate estimates that benefit from a temporal continuity property. Experiments conducted on realistic music pieces show that, given accurate magnitude estimates, this procedure outperforms the state-of-the-art consistent Wiener filter.
Fichier principal
Vignette du fichier
main.pdf (416 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01718718 , version 1 (18-09-2018)
hal-01718718 , version 2 (30-09-2018)

Identifiants

  • HAL Id : hal-01718718 , version 2

Citer

Paul Magron, Roland Badeau, Bertrand David. Model-based STFT phase recovery for audio source separation. IEEE Transactions on Audio, Speech and Language Processing, 2018, 26. ⟨hal-01718718v2⟩
113 Consultations
221 Téléchargements

Partager

Gmail Facebook X LinkedIn More