A new 25+ language child-vocalization dataset, SpeechMaturity, improves self-supervised speech model classification of cry, laugh, and speech maturity, reaching 74.2% unweighted average recall.
By about 6-7 months of age, infants start producing sounds that contain both consonant and vowel elements, form- ing what are known as canonical syllables [1]
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
support 1representative citing papers
citing papers explorer
-
Employing self-supervised learning models for cross-linguistic child speech maturity classification
A new 25+ language child-vocalization dataset, SpeechMaturity, improves self-supervised speech model classification of cry, laugh, and speech maturity, reaching 74.2% unweighted average recall.