Distillation from an XLS-R-based teacher closes about half the correlation gap to ground-truth MOS at 4.3M parameters, while pruning retains near-teacher accuracy at 139M parameters.
Utilizing Self-Supervised Representations for MOS Prediction,
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
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment
Distillation from an XLS-R-based teacher closes about half the correlation gap to ground-truth MOS at 4.3M parameters, while pruning retains near-teacher accuracy at 139M parameters.