Speaker Identification On Voxceleb1
Metrics
Accuracy
Top-1 (%)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy | Top-1 (%) |
|---|---|---|
| ssast-self-supervised-audio-spectrogram | 64.2 | 64.2 |
| autospeech-neural-architecture-search-for | 87.66 | 87.66 |
| ssast-self-supervised-audio-spectrogram | 80.8 | 80.8 |
| atst-audio-representation-learning-with | 94.3 | 94.3 |
| masked-modeling-duo-learning-representations | 94.8 | 94.8 |
| masked-modeling-duo-towards-a-universal-audio | 96.5 | 96.5 |
| masked-autoencoders-that-listen | 94.8 | 94.8 |
| masked-modeling-duo-towards-a-universal-audio | 96.6 | 96.6 |
| masked-autoencoders-that-listen | 94.1 | 94.1 |
| masked-modeling-duo-towards-a-universal-audio | 96.3 | 96.3 |
| contrastive-learning-of-general-purpose-audio | 37.7 | 37.7 |
| ssamba-self-supervised-audio-representation | 70.1 | 70.1 |