S-SONDO distills general audio foundation models into students up to 61 times smaller while retaining up to 96% of teacher performance using only output embeddings.
Neural audio synthesis of musical notes with wavenet autoencoders,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models
S-SONDO distills general audio foundation models into students up to 61 times smaller while retaining up to 96% of teacher performance using only output embeddings.