A novel deep cross-attention fusion of self-supervised learning features yields a 1.1% absolute WER reduction on the Fearless Steps Challenge Phase-4 corpus.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Advancing automatic speech recognition using feature fusion with self-supervised learning features: A case study on Fearless Steps Apollo corpus
A novel deep cross-attention fusion of self-supervised learning features yields a 1.1% absolute WER reduction on the Fearless Steps Challenge Phase-4 corpus.