An interactive audio source separation framework based on non-negative matrix factorization

Abstract : Though audio source separation offers a wide range of applications in audio enhancement and post-production, its performance has yet to reach the satisfactory especially for single-channel mixtures with limited training data. In this paper we present a novel interactive source separation framework that allows end-users to provide feedback at each separation step so as to gradually improve the result. For this purpose, a prototype graphical user interface (GUI) is developed to help users annotating time-frequency regions where a source can be labeled as either active, inactive, or well-separated within the displayed spectrogram. This user feedback information, which is partially new with respect to the state-of-the-art annotations, is then taken into account in a proposed uncertainty-based learning algorithm to constraint the source estimates in next separation step. The considered framework is based on non-negative matrix factorization and is shown to be effective even without using any isolated training data.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics Speech and Signal Processing, May 2014, Florence, Italy. 2014
Liste complète des métadonnées

https://hal.inria.fr/hal-00960717
Contributeur : Alexey Ozerov <>
Soumis le : mardi 18 mars 2014 - 15:57:24
Dernière modification le : mardi 18 mars 2014 - 16:01:48
Document(s) archivé(s) le : mercredi 18 juin 2014 - 13:25:58

Fichier

icassp2014_revised.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00960717, version 1

Citation

Ngoc Duong, Alexey Ozerov, Louis Chevallier, Joel Sirot. An interactive audio source separation framework based on non-negative matrix factorization. IEEE International Conference on Acoustics Speech and Signal Processing, May 2014, Florence, Italy. 2014. 〈hal-00960717〉

Partager

Métriques

Consultations de la notice

847

Téléchargements de fichiers

249