HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

https://halshs.archives-ouvertes.fr/halshs-03647315
Contributor : Alexis Michaud Connect in order to contact the contributor
Submitted on : Wednesday, April 20, 2022 - 2:14:15 PM
Last modification on : Thursday, May 5, 2022 - 12:01:23 PM

File

ComputEL_5_Japhug_ASR.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License

Identifiers

  • 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⟩

Share

Metrics

Record views

17

Files downloads

5