Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MATPAC (SSL, linear eval)

MATPAC (SSL, linear eval)

Reported on 6 benchmarks across 5 tasks · 1 paper · 3 SOTA

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

Audio3 results

Instrument RecognitiononNSynth
Accuracy· 2025-02-17
74.6
best: 80.6 (M2D-CLAP)
SOTA
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031
Audio ClassificationonUrbanSound8K
Accuracy· 2025-02-17
89.4
best: 90.07 (AudioCLIP)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031
Environmental Sound ClassificationonUrbanSound8K
Accuracy· 2025-02-17
89.4
best: 90.07 (AudioCLIP)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031

Music2 results

Music Auto-TaggingonMagnaTagATune
PR-AUC· 2025-02-17
41.1
best: 41.6 (M2D2 AS+)
SOTA
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031
Music Auto-TaggingonMagnaTagATune
ROC AUC· 2025-02-17
91.6
best: 91.8 (M2D2 AS+)
SOTA
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031

Methodology1 result

ClassificationonUrbanSound8K
Accuracy· 2025-02-17
89.4
best: 90.07 (AudioCLIP)
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning arXiv:2502.12031