A cross-attention term retriever estimates which terminology appears in speech and, when its top-k terms are added to the prompt, improves SLM terminology accuracy by 6-17%.
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
-
Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
A cross-attention term retriever estimates which terminology appears in speech and, when its top-k terms are added to the prompt, improves SLM terminology accuracy by 6-17%.