Passer à la navigation principale Passer à la recherche Passer au contenu principal

Supervised group nonnegative matrix factorisation with similarity constraints and applications to speaker identification

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

This paper presents supervised feature learning approaches for speaker identification that rely on nonnegative matrix factorisation. Recent studies have shown that group nonnegative matrix factorisation and task-driven supervised dictionary learning can help performing effective feature learning for audio classification problems. This paper proposes to integrate a recent method that relies on group nonnegative matrix factorisation into a task-driven supervised framework for speaker identification. The goal is to capture both the speaker variability and the session variability while exploiting the discriminative learning aspect of the task-driven approach. Results on a subset of the ESTER corpus prove that the proposed approach can be competitive with I-vectors.

langue originaleAnglais
titre2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
EditeurInstitute of Electrical and Electronics Engineers Inc.
Pages36-40
Nombre de pages5
ISBN (Electronique)9781509041176
Les DOIs
étatPublié - 16 juin 2017
Evénement2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, États-Unis
Durée: 5 mars 20179 mars 2017

Série de publications

NomICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (imprimé)1520-6149

Une conférence

Une conférence2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Pays/TerritoireÉtats-Unis
La villeNew Orleans
période5/03/179/03/17

Empreinte digitale

Examiner les sujets de recherche de « Supervised group nonnegative matrix factorisation with similarity constraints and applications to speaker identification ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation