Keyword Spotting On Google Speech Commands V2 3
評価指標
Accuracy (10-fold)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy (10-fold) | Paper Title | Repository |
|---|---|---|---|
| SSAMBA | 97.4 | SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model | |
| QuaternionNeuralNetwork | 98.53 | Towards on-Device Keyword Spotting using Low-Footprint Quaternion Neural Models |
0 of 2 row(s) selected.