Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs

Abstract:Audio large language models (Audio LLMs) exhibit systematic failures in transcribing code-switching speech despite strong multilingual capabilities. Focusing on English-Mandarin, we identify three failure modes: language omission, translation-instead-of-transcription, and hallucination. We apply Direct Preference Optimization (DPO) to align models, constructing preference pairs in which chosen responses preserve mixed-language content while rejected responses mimic failure patterns. Training three Audio LLMs on 100K pairs (570 hours), we observe consistent behavioral shifts: models learn to preserve language composition rather than translating when prompted for transcription. This alignment yields MER reductions up to 89.6% (in-distribution) and 20.0% (out-of-distribution). Our findings suggest DPO can effectively elicit correct code-switching transcription behavior from multilingual Audio LLMs.

Computation and Language (cs.CL); Sound (cs.SD)

arXiv:2605.23975 [cs.CL]

(or arXiv:2605.23975v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.23975 Focus to learn more arXiv-issued DOI via DataCite

Proc. Interspeech 2026, pp. 6519-6524

https://doi.org/10.21437/Interspeech.2026-110 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.