EAsT-Final + PaSST

Reported on 3 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.

Music2 results

Music Auto-TaggingonMagnaTagATune (clean)
PR-AUC· 2023-06-30
45.9
best: 46.14 (Short-chunk CNN + Res)
Audio Embeddings as Teachers for Music Classification arXiv:2306.17424
Music Auto-TaggingonMagnaTagATune (clean)
ROC-AUC· 2023-06-30
91.2
best: 91.5 (EAsT-KD + PaSST)
Audio Embeddings as Teachers for Music Classification arXiv:2306.17424

Audio1 result

Instrument RecognitiononOpenMIC-2018
mean average precision· 2023-06-30
0.847
best: 0.855 (DyMN-L)
Audio Embeddings as Teachers for Music Classification arXiv:2306.17424