AudioMNIST
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Time Series Classification | AudioMNIST-DS | Error Rate5 | 14 | |
| Time Series Classification | AudioMNIST | Error Rate1.4 | 14 | |
| Speech classification | AudioMNIST (test) | Accuracy96.3 | 12 | |
| Gender Classification | AudioMNIST | Faithfulness60.3 | 10 | |
| Digit Classification | AudioMNIST | Faithfulness25.4 | 10 | |
| Semantic Retrieval | AudioMnist | F1 Score92.2 | 9 | |
| Spoken Digit Classification | AudioMNIST Spoken Digits 1D binarized original 2D | Test Accuracy90.1 | 7 | |
| Digit Recognition | AudioMNIST | Accuracy0.9892 | 3 | |
| Speaker Recognition | AudioMnist (test) | Accuracy70.51 | 2 | |
| Speaker Recognition | AudioMnist (train) | Accuracy71.79 | 2 | |
| Digit Recognition | AudioMnist (test) | Accuracy64.1 | 2 | |
| Digit Recognition | AudioMnist (train) | Accuracy0.7692 | 2 | |
| Audio Classification | AudioMNIST 40-150-10 (test) | Reference Accuracy95.23 | 2 |
Showing 13 of 13 rows