Skip to main navigation Skip to search Skip to main content

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning

  • Yexing Du
  • , Youcheng Pan
  • , Ziyang Ma
  • , Bo Yang
  • , Yifan Yang
  • , Keqi Deng
  • , Xie Chen
  • , Yang Xiang*
  • , Ming Liu*
  • , Bing Qin
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Pengcheng Laboratory
  • Shanghai Jiao Tong University
  • University of Cambridge

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many translation is still limited by the scarcity of parallel data. To address this, we propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks, enabling effective learning in low-resource settings. We trained MLLMs with varying parameter sizes (3B, 7B, and 32B) and evaluated the proposed strategy using the FLEURS and CoVoST-2 datasets. Experimental results show that the proposed strategy achieves state-of-the-art average performance in 15 × 14 language pairs, requiring fewer than 10 hours of speech data per language to achieve competitive results.

Original languageEnglish
Title of host publicationLong Papers
EditorsWanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
PublisherAssociation for Computational Linguistics (ACL)
Pages12466-12478
Number of pages13
ISBN (Electronic)9798891762510
DOIs
StatePublished - 2025
Event63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 - Vienna, Austria
Duration: 27 Jul 20251 Aug 2025

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Country/TerritoryAustria
CityVienna
Period27/07/251/08/25

Fingerprint

Dive into the research topics of 'Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning'. Together they form a unique fingerprint.

Cite this