Table 2 Average ASV performance (EER, %) as a function of noise type and condition
From: Biomimetic multi-resolution analysis for robust speaker recognition
Cond. | Babble (0–24 dB) | White (0–24 dB) | Subway (0–24 dB) | Reverb (200–1,200 ms) | ||||
|---|---|---|---|---|---|---|---|---|
MFCC | Cortical | MFCC | Cortical | MFCC | Cortical | MFCC | Cortical | |
1 | 6.43 | 5.24 | 12.3 | 7.93 | 8.5 | 6.97 | 9.39 | 6.87 |
2 | 11.47 | 9.09 | 18.06 | 12.71 | 14.1 | 11.55 | 13.88 | 9.58 |
3 | 7.33 | 6.31 | 10.86 | 8.87 | 8.89 | 7.84 | 16.70 | 14.96 |
4 | 7.86 | 6.78 | 14.88 | 10.87 | 10.36 | 8.79 | 12.66 | 9.78 |
5 | 6.39 | 5.98 | 8.52 | 7.55 | 7.70 | 6.89 | 14.05 | 10.59 |
6 | 10.45 | 9.95 | 11.04 | 10.48 | 11.12 | 10.39 | 20.00 | 16.14 |
7 | 9.62 | 10.64 | 13.30 | 12.67 | 10.67 | 12.09 | 19.21 | 16.65 |
8 | 5.19 | 5.46 | 7.19 | 6.48 | 6.00 | 6.04 | 12.78 | 9.48 |
9 | 6.84 | 6.00 | 13.58 | 11.46 | 8.94 | 8.59 | 9.43 | 6.84 |