Efficiently Adapting Spoken Language Models for the Singaporean Context

• URL: http://arxiv.org/abs/2607.10092v1
• Date: Sat, 11 Jul 2026 03:11:26 GMT
• Title: Efficiently Adapting Spoken Language Models for the Singaporean Context
• Abstract summary: Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored.<n>We adapt an open-source SLM to the Singaporean Home Team context across five speech tasks in Singapore's four official languages.<n>We also build HTD-multilingual-QA, a 504,853 sample multilingual QA dataset in text and spoken form.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored, especially when the original training data is inaccessible and the use case demands multilingual, spoken-query interaction. We adapt an open-source SLM to the Singaporean Home Team context across five speech tasks in Singapore's four official languages, combining LoRA fine-tuning, a surrogate text-QA dataset that guards against catastrophic forgetting, and a multi-task objective that adapts the CoBa reweighting scheme to speech. We also build HTD-multilingual-QA, a 504,853 sample multilingual QA dataset in text and spoken form. The resulting HT-Moonstone (5B) matches or outperforms SLMs up to 7x its size on most tasks, attains the best accent and gender recognition among all models evaluated, and loses under 2\% of its original speech QA ability.

Related papers

• GigaAM Multilingual: Foundation Model for Underrepresented Languages [63.406165255277195]
  We present GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective.<n>We introduce a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance.
  arXiv  Detail & Related papers  (2026-07-11T15:48:03Z)
• Cross-Lingual Interleaving for Speech Language Models [29.477655980414273]
  Spoken Language Models (SLMs) aim to learn linguistic competence directly from speech using discrete units.<n>We present a cross-lingual interleaving method that mixes speech tokens across languages without textual supervision.
  arXiv  Detail & Related papers  (2025-12-01T16:48:05Z)
• A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations [25.58593495281218]
  We propose a unified speech LLM that jointly performs diarization and ASR in an end-to-end manner.<n>By reformulating the training data format and modifying the inference procedure, our model addresses the ambiguity inherent in pre-segmented audio.
  arXiv  Detail & Related papers  (2025-06-26T01:54:02Z)
• SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs [12.60449414234283]
  SpokenNativQA is the first multilingual and culturally aligned spoken question-answering dataset.<n>The dataset comprises approximately 33,000 naturally spoken questions and answers in multiple languages.
  arXiv  Detail & Related papers  (2025-05-25T14:22:18Z)
• Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models [38.608158064184366]
  We standardize and annotate the largest spoken Singlish corpus, introducing the Multitask National Speech Corpus (MNSC)<n>These datasets support diverse tasks, including Automatic Speech Recognition (ASR), Spoken Question Answering (SQA), Spoken Dialogue Summarization (SDS) and Paralinguistic Question Answering (PQA)<n>We propose SingAudioLLM, a multi-task multimodal model leveraging multimodal large language models to handle these tasks concurrently.
  arXiv  Detail & Related papers  (2025-01-02T03:28:52Z)
• ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation [79.66359274050885]
  We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models. Our approach has demonstrated effectiveness in end-to-end speech-to-text translation tasks.
  arXiv  Detail & Related papers  (2023-05-24T07:42:15Z)
• SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents [70.08842857515141]
  SpokenWOZ is a large-scale speech-text dataset for spoken TOD.<n>Cross-turn slot and reasoning slot detection are new challenges for SpokenWOZ.
  arXiv  Detail & Related papers  (2023-05-22T13:47:51Z)
• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning [98.60739735409243]
  Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks. We introduce XSGD for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts.
  arXiv  Detail & Related papers  (2023-04-03T18:46:01Z)
• QAmeleon: Multilingual QA with Only 5 Examples [71.80611036543633]
  We show how to leverage pre-trained language models under a few-shot learning setting. Our approach, QAmeleon, uses a PLM to automatically generate multilingual data upon which QA models are trained. Prompt tuning the PLM for data synthesis with only five examples per language delivers accuracy superior to translation-based baselines.
  arXiv  Detail & Related papers  (2022-11-15T16:14:39Z)
• SD-QA: Spoken Dialectal Question Answering for the Real World [15.401330338654203]
  We build a benchmark on five languages (Arabic, Bengali, English, Kiswahili, Korean) with more than 68k audio prompts in 24 dialects from 255 speakers. We provide baseline results showcasing the real-world performance of QA systems and analyze the effect of language variety and other sensitive speaker attributes on downstream performance. Last, we study the fairness of the ASR and QA models with respect to the underlying user populations.
  arXiv  Detail & Related papers  (2021-09-24T16:54:27Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)

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.