mlsanityData to 14 Oct 2026

Speech Language Models for Under-Represented Languages: Insights from Wolof

arXiv 2509.15362 ↗First posted 18 Sep 2025cs.CL cs.SD eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

We present our journey in training a speech language model for Wolof, an underrepresented language spoken in West Africa, and share key insights. We first emphasize the importance of collecting large-scale, spontaneous, high-quality unsupervised speech data, and show that continued pretraining HuBERT on this dataset outperforms both the base model and African-centric models on ASR. We then integrate this speech encoder into a Wolof LLM to train the first Speech LLM for this language, extending its capabilities to tasks such as speech translation. Furthermore, we explore training the Speech LLM to perform multi-step Chain-of-Thought before transcribing or translating. Our results show that the Speech LLM not only improves speech recognition but also performs well in speech translation. The models and the code will be openly shared.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 19 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

15 of 19 references.

References · 15

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  5. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 241
  6. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  7. 2023On decoder-only architecture for speech-to-text and large language model integrationcited by 145
  8. 2022Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Languagecited by 110
  9. 2024mHuBERT-147: A Compact Multilingual HuBERT Modelcited by 66
  10. 2023Amphion: An Open-Source Audio, Music and Speech Generation Toolkitcited by 27
  11. 2025Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generationcited by 20
  12. 2024AfriHuBERT: A self-supervised speech representation model for African languagescited by 18
3 more
  1. 2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Contextcited by 8
  2. 2024Kallaama: A Transcribed Speech Dataset about Agriculture in the Three Most Widely Spoken Languages in Senegalcited by 7
  3. 2025Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparisoncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Researchcited by 0
  2. 2026Cross-lingual Matryoshka Representation Learning across Speech and Textcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages
  2. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  3. 2025AfriSpeech-MultiBench: A Verticalized Multidomain Multicountry Benchmark Suite for African Accented English ASR
  4. 2026LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models
  5. 2026AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
  6. 2025MLMA: Towards Multilingual ASR With Mamba-based Architectures
  7. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  8. 2022Mu2SLAM: Multitask, Multilingual Speech and Language Models