aiqbench analysis
This research introduces LLM-HB, a novel framework that leverages large language models to guide hotword biasing specifically for the challenge of code-switching in automatic speech recognition. By integrating mixture-of-experts adaptors and language prediction heads, the method significantly reduces mixed error rates compared to standard baselines, marking a substantive advancement in multilingual ASR capabilities.
LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR
arXiv:2610.16579v1 Announce Type: cross Abstract: Code-switching (CS) speech, characterized by language alternation within a single utterance, is prevalent in multilingual communities and poses challenges to automatic speech recognition (ASR) due to rapid language transitions. We propose LLM-HB, a language-aware large language model-guided hotword biasing framework for code-switching ASR (CS-ASR). The framework incorporates a mixture-of-experts (MoE) adaptor and an auxiliary language prediction head to better capture and differentiate multilingual representations, while hotwords are injected through LLM-based prompting. Experiments on the ASRU2019 code-switching challenge test set demonstrate that LLM-HB achieves a 20.30% relative reduction in mixed error rate (MER) over the baseline, reaching 5.85% MER under a 15-distractor hotword setting. To the best of our knowledge, this is the first work to integrate LLM-guided biasing into code-switching ASR. We further release the extracted ASRU2019 hotword list to support future research.
Abstract:Code-switching (CS) speech, characterized by language alternation within a single utterance, is prevalent in multilingual communities and poses challenges to automatic speech recognition (ASR) due to rapid language transitions. We propose LLM-HB, a language-aware large language model-guided hotword biasing framework for code-switching ASR (CS-ASR). The framework incorporates a mixture-of-experts (MoE) adaptor and an auxiliary language prediction head to better capture and differentiate multilingual representations, while hotwords are injected through LLM-based prompting. Experiments on the ASRU2019 code-switching challenge test set demonstrate that LLM-HB achieves a 20.30% relative reduction in mixed error rate (MER) over the baseline, reaching 5.85% MER under a 15-distractor hotword setting. To the best of our knowledge, this is the first work to integrate LLM-guided biasing into code-switching ASR. We further release the extracted ASRU2019 hotword list to support future research.
Sound (cs.SD); Machine Learning (cs.LG)
arXiv:2610.16579 [cs.SD]
(or arXiv:2610.16579v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2610.16579 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
Proc. Interspeech 2026, 6504-6508
https://doi.org/10.21437/Interspeech.2026-1113 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.
Full text under the publisher's open licence · 243 words
