mlsanityData to 7 Oct 2026

AfriHuBERT: A self-supervised speech representation model for African languages

arXiv 2409.20201 ↗First posted 30 Sep 2024cs.CL cs.SD eess.AScited by 17

Not on the map. Why?

Abstract (arXiv)

In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African languages, we expand this to 1,226 through continued pretraining on 10K+ hours of speech data from diverse sources, benefiting an African population of over 600M. We evaluate AfriHuBERT on two key speech tasks, Spoken Language Identification (SLID) and Automatic Speech Recognition (ASR), using the FLEURS benchmark. Our results show a +3.6% F1 score improvement for SLID and a -2.1% average Word Error Rate (WER) reduction for ASR over mHuBERT-147, and demonstrates competitiveness with larger SSL models such as MMS and XEUS. Further analysis shows that ASR models trained on AfriHuBERT exhibit improved cross-corpus generalization and are competitive in extremely low-resource ASR scenarios.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 30 Sep 2024.

Builds on

36 of 52 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  5. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  7. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  8. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  9. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 462
  10. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  11. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  12. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
24 more
  1. 2024The Faiss librarycited by 370
  2. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 340
  3. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  4. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
  5. 2023Seamless: Multilingual Expressive and Streaming Speech Translationcited by 190
  6. 2022Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuningcited by 149
  7. 2021Textless Speech-to-Speech Translation on Real Datacited by 121
  8. 2020VoxLingua107: a Dataset for Spoken Language Recognitioncited by 118
  9. 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
  10. 2023ML-SUPERB: Multilingual Speech Universal PERformance Benchmarkcited by 70
  11. 2024mHuBERT-147: A Compact Multilingual HuBERT Modelcited by 64
  12. 2024Towards Robust Speech Representation Learning for Thousands of Languagescited by 48
  13. 2022SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translationscited by 35
  14. 2022BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpuscited by 31
  15. 2022A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understandingcited by 18
  16. 2023Zambezi Voice: A Multilingual Speech Corpus for Zambian Languagescited by 18
  17. 2021Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Userscited by 16
  18. 2023ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representationscited by 15
  19. 2024FLEURS-R: A Restored Multilingual Speech Corpus for Generation Taskscited by 13
  20. 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialectscited by 11
  21. 2023Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learningcited by 8
  22. 2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Contextcited by 8
  23. 2024Kallaama: A Transcribed Speech Dataset about Agriculture in the Three Most Widely Spoken Languages in Senegalcited by 7
  24. 2024Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 10.

17 papers.

Sort:

By area:

  1. 2025Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Aheadcited by 15
  2. 2025Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directionscited by 6
  3. 2025Voice of a Continent: Mapping Africa's Speech Technology Frontiercited by 4
  4. 2025Speech Language Models for Under-Represented Languages: Insights from Wolofcited by 2
  5. 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Reviewcited by 2
  6. 2025How much speech data is necessary for ASR in African languages? An evaluation of data scaling in Kinyarwanda and Kikuyucited by 2
  7. 2026Ara-Best-RQ: Multi Dialectal Arabic SSLcited by 1
  8. 2026Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languagescited by 1
  9. 2026Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yor`ub'acited by 1
  10. 2026OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languagescited by 1
  11. 2025Scaling HuBERT for African Languages: From Base to Large and XLcited by 0
  12. 2026Saar-Voice: A Multi-Speaker Saarbr"ucken Dialect Speech Corpuscited by 0
5 more
  1. 2026Sometin Beta Pass Notin: Improving Multilingual ASR for Nigerian Languages via Knowledge Distillationcited by 0
  2. 2026From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausacited by 0
  3. 2026From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languagescited by 0
  4. 2026MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognitioncited by 0
  5. 2026NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Taskcited by 0