Audio Source Separation Based on Convolutive Transfer Function and Frequency-Domain Lasso Optimization

Xiaofei Li 1 Laurent Girin 2, 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 GIPSA-CRISSP - CRISSP
GIPSA-DPC - Département Parole et Cognition
Abstract : This paper addresses the problem of under-determined convolutive audio source separation in a semi-oracle configuration where the mixing filters are assumed to be known. We propose a separation procedure based on the convolutive transfer function (CTF), which is a more appropriate model for strongly reverberant signals than the widely-used multi-plicative transfer function approximation. In the short-time Fourier transform domain, source signals are estimated by minimizing the mixture fitting cost using Lasso optimization, with a $l_1$-norm regularization to exploit the spectral sparsity of source signals. Experiments show that the proposed method achieves satisfactory performance on highly reverberant speech mixtures, with a much lower computational cost compared to time-domain dual techniques.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), Mar 2017, New Orleans, United States. IEEE, ICASSP 2017 - Proceedings, pp.541-545, 2017, 〈10.1109/ICASSP.2017.7952214〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01430754
Contributeur : Team Perception <>
Soumis le : mardi 10 janvier 2017 - 11:18:18
Dernière modification le : vendredi 27 juillet 2018 - 11:04:35
Document(s) archivé(s) le : mardi 11 avril 2017 - 14:11:10

Fichier

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

Identifiants

Citation

Xiaofei Li, Laurent Girin, Radu Horaud. Audio Source Separation Based on Convolutive Transfer Function and Frequency-Domain Lasso Optimization. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), Mar 2017, New Orleans, United States. IEEE, ICASSP 2017 - Proceedings, pp.541-545, 2017, 〈10.1109/ICASSP.2017.7952214〉. 〈hal-01430754〉

Partager

Métriques

Consultations de la notice

679

Téléchargements de fichiers

265