AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
Masked spectrogram modeling using masked autoencoders for learning general-purpose audio repre- sentation.arXiv preprint arXiv:2204.12260,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AudioMosaic: Contrastive Masked Audio Representation Learning
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.