Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context

2024/04/02 by Caubrière, Antoine, Gauthier, Elodie · 3 citations
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2404.02000

Abstract

We present the first self-supervised multilingual speech model trained exclusively on African speech. The model learned from nearly 60 000 hours of unlabeled speech segments in 21 languages and dialects spoken in sub-Saharan Africa. On the SSA subset of the FLEURS-102 dataset, our approach based on a HuBERT_base (0.09B) architecture shows competitive results, for ASR downstream task, compared to the w2v-bert-51 (0.6B) pre-trained model proposed in the FLEURS benchmark, while being more efficient by using 7x less data and 6x less parameters. Furthermore, in the context of a LID downstream task, our approach outperforms FLEURS baselines accuracy by over 22%.

Cited by

• Scaling HuBERT for African Languages: From Base to Large and XL
• Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review
• Speech Language Models for Under-Represented Languages: Insights from Wolof

Related

• AfriHuBERT: A self-supervised speech representation model for African languages
• Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning
• Scaling HuBERT for African Languages: From Base to Large and XL
• Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning
• Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching