PINT uses parallel utterances to train invariant speech tokens, cutting speaker probe accuracy from 93.1% to 1.2% and lowering LM perplexity by 27 to 30% relative to HuBERT and WavLM tokens.
SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities,
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Content is What Remains: Invariant Speech Tokenization from Parallel Utterances
PINT uses parallel utterances to train invariant speech tokens, cutting speaker probe accuracy from 93.1% to 1.2% and lowering LM perplexity by 27 to 30% relative to HuBERT and WavLM tokens.