Table 1 Accuracy rate (%) baselines for different feature extraction techniques
From: Auditory processing-based features for improving speech recognition in adverse acoustic conditions
Channel | MFCC | PLP | GFCC |
|---|---|---|---|
1 | 89.3 | 90.5 | 88.43 |
2 | 77.6 | 77.1 | 80.7 |
3 | 61.7 | 63.8 | 64.5 |
4 | 53.8 | 55.5 | 58.4 |
5 | 57.9 | 57.5 | 64.4 |
6 | 62.5 | 62.2 | 63.6 |
7 | 53.2 | 53.5 | 61.6 |
8 | 72.9 | 73.0 | 71.8 |
9 | 58.4 | 61.8 | 63.2 |
10 | 45.2 | 47.7 | 48.6 |
11 | 41.1 | 43.2 | 45.9 |
12 | 36.2 | 38.9 | 46.1 |
13 | 47.0 | 48.0 | 49.8 |
14 | 38.3 | 40.2 | 46.9 |
Average | 56.7 | 58.0 | 61.0 |