A length-tagged end-to-end speech translation model with a single-pass multi-length beam search improves dubbed-video synchronization with little loss in BLEU.
Model and Data The ST model used in our experiments is multilingual and jointly trained on Spanish (ES) and Korean (KO) data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
extend 1representative citing papers
citing papers explorer
-
Length Aware Speech Translation for Video Dubbing
A length-tagged end-to-end speech translation model with a single-pass multi-length beam search improves dubbed-video synchronization with little loss in BLEU.