EURASIP Journal on Audio, Speech, and Music Processing

Table 2 The PESQ of different graph speech enhancement methods followed by the K-graphs learning method

From: An MMSE graph spectral magnitude estimator for speech signals residing on an undirected multiple graph

PESQ
	Input SNR
Algorithms	−15 dB	−10 dB	−5 dB	0 dB	5 dB
Noisy	0.954	1.079	1.253	1.560	1.924
GWF-KGL	0.984	1.065	1.304	1.633	2.001
GMMSE-KGL	0.995	1.162	1.532	1.934	2.277

Back to article page