SALF-MOS, a compact U-Net-style model using frozen wav2vec features, claims state-of-the-art MOS prediction on four benchmarks with only 1,574 parameters.
TERA: Self-supervised learning of transformer encoder representation for speech,
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.SD 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction
SALF-MOS, a compact U-Net-style model using frozen wav2vec features, claims state-of-the-art MOS prediction on four benchmarks with only 1,574 parameters.