A knowledge-distillation method trains a small language model from CTC speech recognizer outputs, giving a context-dependent internal language model that improves cross-domain decoding by over 13% relative WER.
Single Headed Attention Based Sequence-to-Sequence Model for State- of-the-Art Results on Switchboard-300,
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.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Label-Context-Dependent Internal Language Model Estimation for CTC
A knowledge-distillation method trains a small language model from CTC speech recognizer outputs, giving a context-dependent internal language model that improves cross-domain decoding by over 13% relative WER.