Dedicated context biasing methods cut rare-word error rates by up to 88 percent relative and stayed robust to distractor lists, while speech LLMs were strong on read speech but degraded when prompts grew or were reordered.
Cold fusion: Training seq2seq models together with language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs
Dedicated context biasing methods cut rare-word error rates by up to 88 percent relative and stayed robust to distractor lists, while speech LLMs were strong on read speech but degraded when prompts grew or were reordered.