A 23M-parameter student distilled from HuBERT/WavLM and MERT gets close to teacher-level average accuracy on speech and music benchmarks and outperforms its teachers in few-shot classification.
MERT: Acoustic music understanding model with large-scale self-supervised training,
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
background 1representative citing papers
citing papers explorer
-
Multi-Distillation from Speech and Music Representation Models
A 23M-parameter student distilled from HuBERT/WavLM and MERT gets close to teacher-level average accuracy on speech and music benchmarks and outperforms its teachers in few-shot classification.