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

• URL: http://arxiv.org/abs/2509.15362v2
• Date: Thu, 25 Sep 2025 08:40:33 GMT
• Title: Speech Language Models for Under-Represented Languages: Insights from Wolof
• Authors: Yaya Sy, Dioula Doucouré, Christophe Cerisara, Irina Illina,
• Abstract summary: We present our journey in training a speech language model for Wolof, an underrepresented language spoken in West Africa.<n>We first emphasize the importance of collecting large-scale, spontaneous, high-quality unsupervised speech data.<n>We show that continued pretraining HuBERT on this dataset outperforms both the base model and African-centric models on ASR.
• Score: 9.14632796153174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• OpusLM: A Family of Open Unified Speech Language Models [56.14140121061921]
  The OpusLMs are continuously pre-trained on 213K hours of speech-text pairs and 292B text-only tokens.<n>Technically, this paper articulates our SpeechLM designs on tokenization, multi-stream language models, and multi-stage training strategies.
  arXiv  Detail & Related papers  (2025-06-21T06:30:59Z)
• From TOWER to SPIRE: Adding the Speech Modality to a Text-Only LLM [21.454870778985153]
  We extend an existing large language model (LLMs) to the speech modality via speech discretization and continued pre-training.<n>The resulting open-source model, SPIRE, is able to transcribe and translate English speech input while maintaining TOWER's original performance on translation-related tasks.
  arXiv  Detail & Related papers  (2025-03-13T17:57:32Z)
• Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning [13.113505050543298]
  We introduce a large language model capable of processing speech inputs.<n>We show that tuning it further with reinforcement learning on human preference enables it to adapt better to disordered speech than traditional fine-tuning.
  arXiv  Detail & Related papers  (2024-12-25T00:16:22Z)
• Zero-resource Speech Translation and Recognition with LLMs [38.11535502039386]
  We propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data.<n>We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM.
  arXiv  Detail & Related papers  (2024-12-24T17:37:11Z)
• Self-Powered LLM Modality Expansion for Large Speech-Text Models [62.27700381806554]
  Large language models (LLMs) exhibit remarkable performance across diverse tasks. This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We introduce a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning.
  arXiv  Detail & Related papers  (2024-10-04T04:34:24Z)
• Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech [29.847183061204436]
  This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights.<n>We utilize an end-to-end system with a speech encoder, which is trained to produce token embeddings such that the LLM's response to an expressive speech prompt is aligned with its response to a semantically matching text prompt.
  arXiv  Detail & Related papers  (2024-10-02T01:32:47Z)
• DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data [84.01401439030265]
  Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs)<n>We present a simple yet effective automatic process for creating speech-text pair data.<n>Our model demonstrates general capabilities for speech-related tasks without the need for speech instruction-tuning data.
  arXiv  Detail & Related papers  (2024-09-30T07:01:21Z)
• On decoder-only architecture for speech-to-text and large language model integration [59.49886892602309]
  Speech-LLaMA is a novel approach that effectively incorporates acoustic information into text-based large language models. We conduct experiments on multilingual speech-to-text translation tasks and demonstrate a significant improvement over strong baselines.
  arXiv  Detail & Related papers  (2023-07-08T06:47:58Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM [19.36630667212398]
  We present Spectron, a novel approach to adapting pre-trained large language models (LLMs) to perform spoken question answering (QA) and speech continuation. Key to our approach is a training objective that jointly supervises speech recognition, text continuation, and speech synthesis. Our method surpasses existing spoken language models in speaker preservation and semantic coherence.
  arXiv  Detail & Related papers  (2023-05-24T15:39:43Z)
• The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation [13.352795145385645]
  Speech translation (ST) is a good means of pretraining speech models for end-to-end spoken language understanding. We show that our models reach higher performance over baselines on monolingual and multilingual intent classification. We also create new benchmark datasets for speech summarization and low-resource/zero-shot transfer from English to French or Spanish.
  arXiv  Detail & Related papers  (2023-05-16T17:53:03Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.