Table 3 Calculation results in the noise matching condition when IBM is the training target
From: Research on monaural speech segregation based on feature selection
Feature and feature group | STOI | PESQ | SDR | SNR |
|---|---|---|---|---|
AMS | 0.7527 | 2.2276 | 8.4709 | 8.4105 |
AMS + GF | 0.8202 | 2.4656 | 10.8801 | 10.6167 |
AMS + GF + MRCG | 0.8277 | 2.4594 | 10.9181 | 10.7706 |
AMS + MFCC | 0.8208 | 2.4422 | 10.5386 | 10.3851 |
AMS + MFCC + GF | 0.8259 | 2.4537 | 10.7574 | 10.6132 |
AMS + MFCC + GF + MRCG | 0.8779 | 2.4314 | 10.9985 | 10.8134 |
AMS + MFCC + MRCG | 0.8270 | 2.4574 | 10.9764 | 10.7877 |
AMS + MRCG | 0.8250 | 2.4420 | 10.8013 | 10.6818 |
GF | 0.8175 | 2.4599 | 10.7795 | 10.3668 |
GF + MRCG | 0.8242 | 2.4439 | 10.8542 | 10.6339 |
MFCC | 0.8170 | 2.4585 | 10.4417 | 10.0997 |
MFCC + GF | 0.8225 | 2.4759 | 10.6328 | 10.2979 |
MFCC + GF + MRCG | 0.8265 | 2.4323 | 10.8243 | 10.6493 |
MFCC + MRCG | 0.8252 | 2.4542 | 10.9840 | 10.6970 |
MRCG | 0.8201 | 2.4485 | 10.5185 | 10.3349 |