| Benchmark | Model | Rank | Results |
|---|---|---|---|
| sound-event-detection-on-desed | HTS-AT | #3 | event-based F1 score: 50.7 |
| audio-tagging-on-audioset | HTS-AT (Ensemble) | #8 | mean average precision: 0.487 |
| audio-classification-on-esc-50 | HTS-AT | #9 | Top-1 Accuracy: 97.0PRE-TRAINING DATASET: AudioSet… |
| audio-classification-on-audioset | HTS-AT (Ensemble) | #15 | Test mAP: 0.487 |
| keyword-spotting-on-google-speech-commands | HTS-AT | #27 | Google Speech Commands V2 35: 98.0 |