Multi-Format Contrastive

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Audio2 results

Audio ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2021-03-11
90.5
best: 99.1 (OmniVec2)
SOTA
Multi-Format Contrastive Learning of Audio Representations arXiv:2103.06508
Audio ClassificationonAudioSet
Test mAP· 2021-03-11
0.376
best: 0.558 (OmniVec2)
Multi-Format Contrastive Learning of Audio Representations arXiv:2103.06508

Methodology2 results

ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2021-03-11
90.5
best: 99.1 (OmniVec2)
SOTA
Multi-Format Contrastive Learning of Audio Representations arXiv:2103.06508
ClassificationonAudioSet
Test mAP· 2021-03-11
0.376
best: 0.558 (OmniVec2)
Multi-Format Contrastive Learning of Audio Representations arXiv:2103.06508