A multi-grained fusion method that jointly uses token-level and phrase-level scores from ASR and LLM improves keyword recognition in contextual ASR.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Contextual ASR via Multi-grained Fusion with Large Language Models
A multi-grained fusion method that jointly uses token-level and phrase-level scores from ASR and LLM improves keyword recognition in contextual ASR.