Maxime Fily


pdf bib
Establishing degrees of closeness between audio recordings along different dimensions using large-scale cross-lingual models
Maxime Fily | Guillaume Wisniewski | Severine Guillaume | Gilles Adda | Alexis Michaud
Findings of the Association for Computational Linguistics: EACL 2024

In the highly constrained context of low-resource language studies, we explore vector representations of speech from a pretrained model to determine their level of abstraction with regard to the audio signal. We propose a new unsupervised method using ABX tests on audio recordings with carefully curated metadata to shed light on the type of information present in the representations. ABX tests determine whether the representations computed by a multilingual speech model encode a given characteristic. Three experiments are devised: one on room acoustics aspects, one on linguistic genre, and one on phonetic aspects. The results confirm that the representations extracted from recordings with different linguistic/extra-linguistic characteristics differ along the same lines. Embedding more audio signal in one vector better discriminates extra-linguistic characteristics, whereas shorter snippets are better to distinguish segmental information. The method is fully unsupervised, potentially opening new research avenues for comparative work on under-documented languages.


pdf bib
Fine-tuning pre-trained models for Automatic Speech Recognition, experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
Séverine Guillaume | Guillaume Wisniewski | Cécile Macaire | Guillaume Jacques | Alexis Michaud | Benjamin Galliot | Maximin Coavoux | Solange Rossato | Minh-Châu Nguyên | Maxime Fily
Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages

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.