Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context
Domaine:
natural language processingType de record:
papermodel
Créateur:
Cau
Hôte:
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\%. To appear in AfricaNLP 2024
Similaires
Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language ModelsAfriHuBERT: A self-supervised speech representation model for African languagesXLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech RecognitionBenchmarking Self-Supervised Speech Models on Multilingual Nigerian SpeechFine-Tuned Self-Supervised Speech Representations for Language Diarization in Multilingual Code-Switched SpeechLarge vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning