Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation

ACL ARR 2025 May Submission5567 Authors

Abstract: Language diversity presents a significant challenge in speech-to-text (S2T) tasks, such as automatic speech recognition and translation. Traditional multi-lingual multi-task training approaches aim to address this by jointly optimising multiple speech recognition and translation tasks across various languages. While models like Whisper, built on these strategies, demonstrate strong performance, they still face issues of high computational cost, language interference, suboptimal training configurations, and limited extensibility. To overcome these challenges, we introduce LoRS-Merging (low-rank and sparse model merging), a novel technique designed to efficiently integrate models trained on different languages or tasks while preserving performance and reducing computational overhead. LoRS-Merging combines low-rank and sparse pruning to retain essential structures while eliminating redundant parameters, mitigating language interference, and enhancing extensibility. Experimental results across 10 languages demonstrate that LoRS-Merging significantly outperforms multi-lingual multi-task training, sequential training, and other merging methods, achieving over 20% improvement in normalised performance. Our findings suggest that model merging, particularly LoRS-Merging, is a scalable and effective complement to traditional multi-lingual training strategies for S2T applications.

Paper Type: Long

Research Area: Speech Recognition, Text-to-Speech and Spoken Language Understanding

Research Area Keywords: automatic speech recognition, speech translation, speech technologies

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: Catalan, German, Spanish, French, Italian, Indonesian, Dutch, Portuguese, Russian, Swedish

Keywords: automatic speech recognition, speech translation, speech technologies

Submission Number: 5567