Research Article
Direct Recovery of Clean Speech Using a Hybrid Noise Suppression Algorithm for Robust Speech Recognition System
Table 4
Recognition results for comparison targets.
| | Clean | Avg 0–20 | −5 |
| MFCC | 99.42 | 71.80 | 13.39 | SS | 99.32 | 72.42 | 25.26 | CMVN | 99.32 | 77.78 | 13.90 | STSA | 99.26 | 80.12 | 20.31 | AFE | 99.20 | 82.23 | 24.77 | MVA | 99.20 | 84.15 | 26.24 |
|
|