EURASIP Journal on Audio, Speech, and Music Processing

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 (%)
Method	Acoustic model	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

Back to article page