Arrêt de service programmé du vendredi 10 juin 16h jusqu’au lundi 13 juin 9h. Pour en savoir plus
Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)

Abstract : This is a report on results obtained in the development of speech recognition tools intended to support linguistic documentation efforts. The test case is an extensive fieldwork corpus of Japhug, an endangered language of the Trans-Himalayan (Sino-Tibetan) family. The goal is to reduce the transcription workload of field linguists. The method used is a deep learning approach based on the language-specific tuning of a generic pre-trained representation model, XLS-R, using a Transformer architecture. We note difficulties in implementation, in terms of learning stability. But this approach brings significant improvements nonetheless. The quality of phonemic transcription is improved over earlier experiments; and most significantly, the new approach allows for reaching the stage of automatic word recognition. Subjective evaluation of the tool by the author of the training data confirms the usefulness of this approach.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://halshs.archives-ouvertes.fr/halshs-03647315
Contributeur : Alexis Michaud Connectez-vous pour contacter le contributeur
Soumis le : mercredi 20 avril 2022 - 14:14:15
Dernière modification le : samedi 21 mai 2022 - 14:06:01

Fichier

ComputEL_5_Japhug_ASR.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité - Pas d'utilisation commerciale - Partage selon les Conditions Initiales 4.0 International License

Identifiants

  • HAL Id : halshs-03647315, version 1

Citation

Séverine Guillaume, Guillaume Wisniewski, Cécile Macaire, Guillaume Jacques, Alexis Michaud, et al.. Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family). 5th Workshop on Computational Methods for Endangered Languages (ComputEL-5), May 2022, Dublin, Ireland. ⟨halshs-03647315⟩

Partager

Métriques

Consultations de la notice

25

Téléchargements de fichiers

18