SRPSE removes content-agnostic components from speech representations using orthogonal projection, supervision from speaker and SNR labels, and consistency and mutual information losses, improving speech translation quality.
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
-
Representation Purification for End-to-End Speech Translation
SRPSE removes content-agnostic components from speech representations using orthogonal projection, supervision from speaker and SNR labels, and consistency and mutual information losses, improving speech translation quality.