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.
Test time adaptation via conjugate pseudo-labels,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 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.