PaSST

Reported on 2 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 TaggingonAudioSet
mean average precision· uses extra data· 2021-10-11
0.496
best: 0.512 (CAV-MAE (Audio-Visual))
SOTA
Efficient Training of Audio Transformers with Patchout arXiv:2110.05069
Instrument RecognitiononOpenMIC-2018
mean average precision· uses extra data· 2021-10-11
0.843
best: 0.855 (DyMN-L)
SOTA
Efficient Training of Audio Transformers with Patchout arXiv:2110.05069