Jointly refining ASR transcripts and ST translations with an LLM improves BLEU and COMET on MuST-C and CoVoST 2 across seven translation tasks.
Leveraging gpt-4 for automatic translation post-editing,
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Speech Translation Refinement using Large Language Models
Jointly refining ASR transcripts and ST translations with an LLM improves BLEU and COMET on MuST-C and CoVoST 2 across seven translation tasks.