Principal dimensions of self-supervised speech features encode isolated speaker characteristics including pitch, intensity, noise levels, and formants.
Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features
Principal dimensions of self-supervised speech features encode isolated speaker characteristics including pitch, intensity, noise levels, and formants.