Table 4 Test the effect of speech speed on model performance
From: Multi-task deep cross-attention networks for far-field speaker verification and keyword spotting
| Â | Speed | Seen | Unseen | ||||
|---|---|---|---|---|---|---|---|
| Â | EER (%) | minDCF | Acc (%) | EER (%) | minDCF | Acc (%) | |
Without noise | Normal | 0.03 | 0.004 | 99.00 | 1.36 | 0.093 | 96.87 |
Fast | 0.13 | 0.002 | 97.69 | 1.49 | 0.096 | 94.32 | |
With noise | Normal | 0.76 | 0.038 | 96.49 | 3.37 | 0.180 | 94.03 |
Fast | 1.16 | 0.055 | 94.83 | 4.30 | 0.216 | 91.67 | |