Prestilien Djionang Pindoh ; Paulin Melatagia Yonta - Self-supervised and multilingual learning applied to the Wolof, Swahili and Fongbe

arima:13416 - Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, February 11, 2025, Volume 42 - Special issue CRI 2023 - 2024/2025 - https://doi.org/10.46298/arima.13416
Self-supervised and multilingual learning applied to the Wolof, Swahili and FongbeArticle

Authors: Prestilien Djionang Pindoh 1; Paulin Melatagia Yonta ORCID2,1

  • 1 Département d'Informatique [Yaoundé I]
  • 2 Unité de modélisation mathématique et informatique des systèmes complexes [Bondy]

Under-resourced languages encounter substantial obstacles in speech recognition owing to the scarcity of resources and limited data availability, which impedes their development and widespread adoption. This paper presents a representation learning model that leverages existing frameworks based on self-supervised learning techniques—specifically, Contrastive Predictive Coding (CPC), wav2vec, and a bidirectional variant of CPC—by integrating them with multilingual learning approaches. We apply this model to three African languages: Wolof, Swahili, and Fongbe. Our evaluation of the resulting representations in a downstream task, automatic speech recognition, utilizing an architecture analogous to DeepSpeech, reveals the model’s capacity to discern language specific linguistic features. The results demonstrate promising performance, achieving Word Error Rates (WER) of 61% for Fongbe, 72% for Wolof, and 88% for Swahili. These findings underscore the potential of our approach in advancing speech recognition capabilities for under-resourced languages, particularly within the African linguistic landscape.


Volume: Volume 42 - Special issue CRI 2023 - 2024/2025
Published on: February 11, 2025
Accepted on: January 17, 2025
Submitted on: April 16, 2024
Keywords: Self-supervised learning,Multilingual representation learning,Automatic speech recognition,Under-resourced languages,Apprentissage auto-supervisé,Apprentissage de représentations multilingues,Reconnaissance automatique de la parole,Langues peu dotées,[INFO]Computer Science [cs]

Consultation statistics

This page has been seen 89 times.
This article's PDF has been downloaded 49 times.