Scalable Expansion of Multilingual Speech LLMs for ASR: A Continual Learning Approach

Lorenzo Concina, Marco Matassoni, Alessio Brutti


Abstract
Speech Large Language Models have recently enabled the processing of spoken language by coupling powerful language models (LLMs) with pre-trained speech encoders. However, their multilingual scalability remains limited, particularly for low - resource and unseen languages, while naïve fine- tuning often triggers catastrophic forgetting of previously learned languages. This work investigates how Continual Learning (CL) can be used to sustainably expand multilingual Speech LLMs. We first demonstrate that multilingual projectors can be efficiently bootstrapped to new languages , even with extremely small datasets, but at the cost of severe degradation on the original supported languages. To address this, we adopt rehearsal-based CL strategies and show that interleaving even small amounts of replay data effectively stabilizes multilingual performance. Through extensive ablations, we quantify the minimum rehearsal budget required to prevent forgetting and identify fragile languages that require more targeted reinforcement. We further evaluate sequential acquisition of four linguistically diverse languages (Ukrainian, Japanese, Thai, and Vietnamese), revealing the trade -offs between buffer size and long- term stability. Finally, based on these empirical observations, we propose a Fragility-Based Sampling heuristic as a pathway to allocate rehearsal data more efficiently by tiering languages according to their stability thresholds. Our findings provide a practical roadmap for scalable, resource-efficient multilingual expansion of Speech LLMs, enabling inclusive ASR systems that can grow over time without sacrificing prior knowledge.
Anthology ID:
2026.speakable-1.7
Volume:
Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Nina Hosseini-Kivanani, Alessio Brutti, Marco Matassoni, Sandipana Dowerah, Davide Liga, Christoph Schommer
Venues:
SPEAKABLE | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
59–65
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-speakable-07
DOI:
10.63317/5b86xj9f28dp
Bibkey:
Cite (ACL):
Lorenzo Concina, Marco Matassoni, and Alessio Brutti. 2026. Scalable Expansion of Multilingual Speech LLMs for ASR: A Continual Learning Approach. In Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026, pages 59–65, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Scalable Expansion of Multilingual Speech LLMs for ASR: A Continual Learning Approach (Concina et al., SPEAKABLE 2026)
Copy Citation: