Hybrid Network For End-To-End Text-Independent Speaker Identification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Hybrid Network For End-To-End Text-Independent Speaker Identification

Wajdi Ghezaiel
  • Fonction : Auteur
  • PersonId : 1078474
Luc Brun
  • Fonction : Auteur
  • PersonId : 936962

Résumé

Deep learning has recently improved the performance of Speaker Identification (SI) systems. Promising results have been obtained with Convolutional Neural Networks (CNNs). This success is mostly driven by the advent of large datasets. However in the context of decentralized commercial applications, collection of large amount of training data is not always possible. In addition, robustness of a SI system is adversely effected by short utterances. Therefore, in this paper, we propose a novel text-independent speaker identification system able to identify speakers by learning from only few training short utterances examples. To achieve this, we combine a two-layer wavelet scattering network coupled with a CNN. The proposed architecture takes variable length speech segments. To evaluate the effectiveness of the proposed approach, Timit and Librispeech datasets are used in the experiments. Our experiments shows that our hybrid architecture provides satisfactory results under the constraints of short and limited number of utterances. These experiments also show that our hybrid architecture are competitive with the state of the art.

Mots clés

Fichier principal
Vignette du fichier
icpr_paper_final.pdf (381.77 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03086433 , version 1 (22-12-2020)

Identifiants

Citer

Wajdi Ghezaiel, Luc Brun, Olivier Lézoray. Hybrid Network For End-To-End Text-Independent Speaker Identification. Internation conference on Pattern Recognition, Jan 2021, Milan (virtual), Italy. ⟨10.1109/ICPR48806.2021.9413293⟩. ⟨hal-03086433⟩
72 Consultations
343 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More