Improving training datasets for resource-constrained speaker recognition neural networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Improving training datasets for resource-constrained speaker recognition neural networks

Résumé

Tackling the increase in complexity, which is now the main factor of improvement in deep learning, this paper proposes a new algorithm of data selection for training speaker recognition systems. The method starts from an initial training dataset, then the algorithm scans new data to determine the most useful speakers for completing the initial ones. The resulting training dataset improves the model, in terms of accuracy and ability to generalize, while maintaining the learning complexity reasonable. This algorithm is unsupervised, as it does not need any metadata on the new utterances and, therefore, compatible with self-supervised learning. By selecting only 30% of the speakers from a new database, the proposed algorithm is able to achieve very similar performances to the system with all speakers added.
Fichier principal
Vignette du fichier
CAMERA_READY_IS2023_Selection_of_training_data.pdf (225.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04156025 , version 1 (07-07-2023)

Identifiants

  • HAL Id : hal-04156025 , version 1

Citer

Pierre-Michel Bousquet, Mickael Rouvier. Improving training datasets for resource-constrained speaker recognition neural networks. InterSpeech 2023, Aug 2023, Dublin, Ireland. ⟨hal-04156025⟩
34 Consultations
46 Téléchargements

Partager

Gmail Facebook X LinkedIn More