Unsupervised Blind Source Separation with Variational Auto-Encoders - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Unsupervised Blind Source Separation with Variational Auto-Encoders

Résumé

Supervised source separation requires expensive synthetic datasets containing clean, ground truth-source signals, while unsupervised separation requires only data mixtures. Existing unsupervised methods still use supervision to avoid over-separation and compete with fully supervised methods. We present a new method of completely unsupervised single-channel blind source separation, based on variational auto-encoding, that automatically learns the correct number of sources in data mixtures and quantitatively outperforms the existing methods. A deep inference network disentangles (separates) data mixtures into low-dimensional latent source variables. A deep generative network individually decodes each latent source into its source signal, such that their sum represents the given mixture. Qualitative and quantitative results from separation experiments on pairs of randomly mixed MNIST handwritten digits and mixed audio spectrograms demonstrate that our method outperforms stateof-the-art unsupervised and semi-supervised methods, showing promise as a solution to this long-standing problem in computer vision and audition.
Fichier principal
Vignette du fichier
2021_eusipco_vae_camera_ready.pdf (1.4 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03255341 , version 1 (17-05-2022)

Identifiants

  • HAL Id : hal-03255341 , version 1

Citer

Julian Neri, Roland Badeau, Philippe Depalle. Unsupervised Blind Source Separation with Variational Auto-Encoders. 29th European Signal Processing Conference (EUSIPCO 2021), Aug 2021, Dublin, Ireland. ⟨hal-03255341⟩
130 Consultations
571 Téléchargements

Partager

Gmail Facebook X LinkedIn More