An Improved Unsupervised Single-Channel Speech Separation Algorithm for Processing Speech Sensor Signals

Table 7

Efficiency comparison of speech separation effect.

	Index
Method	PESQ	STOI
Deep neural networks (DNN) [55]	0.694	0.106
Recurrent deep stacking networks (RDSN) [55]	0.823	0.112
CNMF + JADE+ adaptive wavelet transform	0.305	0.106