Modeling each phoneme as a 32-component Gaussian mixture of self-supervised speech features improves atypical pronunciation scoring on four of five datasets, with S3Ms showing stronger allophonic structure than MFCCs or Mel spectrograms.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment
Modeling each phoneme as a 32-component Gaussian mixture of self-supervised speech features improves atypical pronunciation scoring on four of five datasets, with S3Ms showing stronger allophonic structure than MFCCs or Mel spectrograms.