mlsanityData to 14 Oct 2026

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

arXiv 2404.02000 ↗First posted 2 Apr 2024cs.CL cs.LG cs.SDcited by 8

Not on the map. Why?

Abstract (arXiv)

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 HuBERTbase (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%.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

17 of 21 references.

References · 17

  1. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  2. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  3. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  4. 2019How multilingual is Multilingual BERT?cited by 645
  5. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  6. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
  7. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  8. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 347
  9. 2020VoxLingua107: a Dataset for Spoken Language Recognitioncited by 122
  10. 2022AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languagescited by 46
  11. 2022SERENGETI: Massively Multilingual Language Models for Africacited by 40
  12. 2023AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASRcited by 35
5 more
  1. 2022A Survey of Multilingual Models for Automatic Speech Recognitioncited by 21
  2. 2021BembaSpeech: A Speech Recognition Corpus for the Bemba Languagecited by 14
  3. 2022Speech Resources in the Tamasheq Languagecited by 13
  4. 2022KenSwQuAD -- A Question Answering Dataset for Swahili Low Resource Languagecited by 12
  5. 2022Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learningcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 7.

8 papers.

  1. 2024AfriHuBERT: A self-supervised speech representation model for African languagescited by 18
  2. 2025Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Aheadcited by 16
  3. 2025Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directionscited by 6
  4. 2025Voice of a Continent: Mapping Africa's Speech Technology Frontiercited by 4
  5. 2025Speech Language Models for Under-Represented Languages: Insights from Wolofcited by 2
  6. 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Reviewcited by 2
  7. 2025Scaling HuBERT for African Languages: From Base to Large and XLcited by 0
  8. 2025Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Researchcited by 0