Adding text CTC alignment, hierarchical encoding, dense attention decoding, and warm-start transfer learning improves sign-to-text translation on PHOENIX14T and CSL-Daily over a pure-attention baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improvement in Sign Language Translation Using Text CTC Alignment
Adding text CTC alignment, hierarchical encoding, dense attention decoding, and warm-start transfer learning improves sign-to-text translation on PHOENIX14T and CSL-Daily over a pure-attention baseline.