Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries
Quick summary
arXiv:2601.18899v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a pretrained LLM via a lightweight connector. Prior work trains a separate connector per language, overlooking linguistic relatedness. We propose an efficient and novel connector-sharing strategy based on linguistic family membership, enabling one connector per family, and empirically validate its effectiveness across two multilingual LLMs and two real-world corpora spannin
Key takeaways
- arXiv:2601.18899v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a pretrained LLM via a lightweight connector.
- Prior work trains a separate connector per language, overlooking linguistic relatedness.
- We propose an efficient and novel connector-sharing strategy based on linguistic family membership, enabling one connector per family, and empirically validate its effectiveness across two multilingual LLMs and two real-world corpora spannin
Why it matters
“Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments