Table 2 Accuracy rates (%) for the different extraction techniques
From: Auditory processing-based features for improving speech recognition in adverse acoustic conditions
Channel | GFCC-MS | GFCC-MS-NL | GFCC-NL |
|---|---|---|---|
1 | 87.3 | 89.9 | 89.6 |
2 | 80.7 | 83.4 | 81.1 |
3 | 62.6 | 72.8 | 70.9 |
4 | 56.0 | 69.2 | 65.6 |
5 | 64.5 | 71.6 | 69.4 |
6 | 62.6 | 73.2 | 70.1 |
7 | 62.0 | 66.9 | 68 |
8 | 69.7 | 74.4 | 71 |
9 | 61.7 | 63.8 | 62.4 |
10 | 48.2 | 52.3 | 51.9 |
11 | 44.5 | 51.2 | 50.1 |
12 | 43.0 | 50.8 | 48.4 |
13 | 47.2 | 54.3 | 51.6 |
14 | 46.8 | 50.4 | 50.2 |
Average | 59.8 | 64.3 | 66.0 |