Alpha-stable low-rank plus residual decomposition for speech enhancement - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Alpha-stable low-rank plus residual decomposition for speech enhancement

Résumé

In this study, we propose a novel probabilistic model for separating clean speech signals from noisy mixtures by decomposing the mixture spectrograms into a structured speech part and a more flexible residual part. The main novelty in our model is that it uses a family of heavy-tailed distributions, so called the α-stable distributions, for modeling the residual signal. We develop an expectation-maximization algorithm for parameter estimation and a Monte Carlo scheme for posterior estimation of the clean speech. Our experiments show that the proposed method outperforms relevant factorization-based algorithms by a significant margin.
Fichier principal
Vignette du fichier
2017102794510_839706_2832.pdf (310.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01714909 , version 1 (22-02-2018)

Identifiants

Citer

Umut Şimşekli, Halil Erdogan, Simon Leglaive, Antoine Liutkus, Roland Badeau, et al.. Alpha-stable low-rank plus residual decomposition for speech enhancement. ICASSP: International Conference on Acoustics, Speech, and Signal Processing, Apr 2018, Calgary, Canada. pp.651-655, ⟨10.1109/ICASSP.2018.8461539⟩. ⟨hal-01714909⟩
496 Consultations
433 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More