Autoregressive prediction over discrete cochlear tokens yields a speech representation that beats prior self-supervised models on lexical-semantic similarity and is competitive on SUPERB tasks.
Over-reliance on english hinders cognitive science,
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
unclear 1representative citing papers
citing papers explorer
-
Representing Speech Through Autoregressive Prediction of Cochlear Tokens
Autoregressive prediction over discrete cochlear tokens yields a speech representation that beats prior self-supervised models on lexical-semantic similarity and is competitive on SUPERB tasks.