MATPAC (SSL model, linear eval)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio2 results

Audio ClassificationonESC-50
Accuracy (5-fold)· 2025-02-17
93.5
best: 99.1 (OmniVec2)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031
Audio ClassificationonESC-50
Top-1 Accuracy· 2025-02-17
93.5
best: 99.1 (OmniVec2)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031

Methodology2 results

ClassificationonESC-50
Accuracy (5-fold)· 2025-02-17
93.5
best: 99.1 (OmniVec2)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031
ClassificationonESC-50
Top-1 Accuracy· 2025-02-17
93.5
best: 99.1 (OmniVec2)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031