NAC token sequences, especially 3-grams, fit Zipf's and Heaps' laws, and their fitted statistics correlate, though weakly and with confounds, with ASR error rates and UTMOS scores.
Analysing discrete self supervised speech representation for spoken language modeling,
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
-
Analysing the Language of Neural Audio Codecs
NAC token sequences, especially 3-grams, fit Zipf's and Heaps' laws, and their fitted statistics correlate, though weakly and with confounds, with ASR error rates and UTMOS scores.