Audio Classification On Speech Commands 1
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| EAT | 98.3±0.04 | EAT: Self-Supervised Pre-Training with Efficient Audio Transformer | |
| AST-S | 98.11±0.05 | AST: Audio Spectrogram Transformer | |
| PDC | 97.8 | Augmenting Deep Classifiers with Polynomial Neural Networks | |
| ASM-RH | 96.51 | Mixer is more than just a model | - |
| EfficientLEAF | 95.2 | EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use | |
| melspect | 95.1 | EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use | |
| LEAF | 95.1 | EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use |
0 of 7 row(s) selected.