Slowly decaying the fraction of aligned text interleaved with speech units during LLM fine-tuning improves speech-to-speech translation, most for low-resource languages.
The CVSS corpus is a widely used corpus for multilingual S2ST, built by speech synthe- sis from the CoV oST2 [36] speech-to-text translation corpus
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
Slowly decaying the fraction of aligned text interleaved with speech units during LLM fine-tuning improves speech-to-speech translation, most for low-resource languages.