NEURO-STEERED MUSIC SOURCE SEPARATION WITH EEG-BASED AUDITORY ATTENTION DECODING AND CONTRASTIVE-NMF - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année :

NEURO-STEERED MUSIC SOURCE SEPARATION WITH EEG-BASED AUDITORY ATTENTION DECODING AND CONTRASTIVE-NMF

(1, 2, 3) , (1, 2, 3) , (1, 2, 3)
1
2
3

Résumé

We propose a novel informed music source separation paradigm, which can be referred to as neuro-steered music source separation. More precisely, the source separation process is guided by the user's selective auditory attention decoded from his/her EEG response to the stimulus. This high-level prior information is used to select the desired instrument to isolate and to adapt the generic source separation model to the observed signal. To this aim, we leverage the fact that the attended instrument's neural encoding is substantially stronger than the one of the unattended sources left in the mixture. This "contrast" is extracted using an attention decoder and used to inform a source separation model based on non-negative matrix fac-torization named Contrastive-NMF. The results are promising and show that the EEG information can automatically select the desired source to enhance and improve the separation quality.
Fichier principal
Vignette du fichier
C-NMF-Hal.pdf (1.16 Mo) Télécharger le fichier
Vignette du fichier
C-NMF_poster.pdf (3.3 Mo) Télécharger le fichier
Vignette du fichier
C-NMF_slides.pdf (8.55 Mo) Télécharger le fichier
Vignette du fichier
Update-rule-C-NMF.pdf (136.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02978978 , version 1 (26-10-2020)
hal-02978978 , version 2 (03-02-2021)
hal-02978978 , version 3 (05-02-2021)
hal-02978978 , version 4 (05-08-2021)

Identifiants

Citer

Giorgia Cantisani, Slim Essid, Gael Richard. NEURO-STEERED MUSIC SOURCE SEPARATION WITH EEG-BASED AUDITORY ATTENTION DECODING AND CONTRASTIVE-NMF. 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto (virtual conference), Canada. ⟨10.1109/ICASSP39728.2021.9413841⟩. ⟨hal-02978978v4⟩
702 Consultations
714 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More