Skip to main content

Advertisement

Table 17 Experimental results on the real reverberant data using GSS and JSR[10]

From: Single-channel dereverberation by feature mapping using cascade neural networks for robust distant speaker identification and speech recognition

Method Acoustic model Digit accuracy (%)
InCar Lounge MeetR Office Average
GSS Multi-rt 86.32 76.67 85.65 83.29 82.98
GSS + CMN Multi-rt 88.88 83.07 89.32 92.52 88.45
JSR Clean 84.71 67.32 92.55 95.23 84.95
JSR + CMN Clean 87.62 79.74 90.19 93.30 87.71