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

arXiv:2404.02000v1 Announce Type: cross
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 …

abstract africa arxiv context cs.cl cs.lg cs.sd dataset eess.as languages multilingual pre-training representation speech spoken training type