An auto-step selection mechanism that uses acoustic confidence and language model scores to pick the best adaptation step for each utterance improves ASR word error rate when combined with linguistic rescoring.
SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR
An auto-step selection mechanism that uses acoustic confidence and language model scores to pick the best adaptation step for each utterance improves ASR word error rate when combined with linguistic rescoring.