PHASE SHIFTED BEDROSIAN FILTERBANK: AN INTERPRETABLE AUDIO FRONT-END FOR TIME-DOMAIN AUDIO SOURCE SEPARATION - Equipe Signal, Statistique et Apprentissage Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

PHASE SHIFTED BEDROSIAN FILTERBANK: AN INTERPRETABLE AUDIO FRONT-END FOR TIME-DOMAIN AUDIO SOURCE SEPARATION

Résumé

The use of a parameterized encoders or audio front-ends has shown promises in improving the interpretability of time domain single-channel source separation models such as Conv-TasNet. This type of filters also allows a potential reduction of the computational cost since larger encoder filters can be used. In this work, we propose to build a new parameterization of such encoder filter-bank which allows gaining interpretability while keeping flexibility. Based on the Hilbert transform and the Bedrosian theorem, we propose to build phase-shifted set of filters by modulating sinusoids through freely learned low pass filters. We show that the use of these filters allows to keep the same performances when using small filters and even improve them when using large filters.
Fichier principal
Vignette du fichier
Mathieu.pdf (351.1 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03708610 , version 1 (29-06-2022)

Identifiants

Citer

Félix Mathieu, Thomas Courtat, Gael Richard, Geoffroy Peeters. PHASE SHIFTED BEDROSIAN FILTERBANK: AN INTERPRETABLE AUDIO FRONT-END FOR TIME-DOMAIN AUDIO SOURCE SEPARATION. ICASSP, May 2022, Singapour, Singapore. ⟨10.1109/ICASSP43922.2022.9746122⟩. ⟨hal-03708610⟩
139 Consultations
103 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More