EURASIP Journal on Audio, Speech, and Music Processing

Table 14 The STOI of different methods for Babble noise

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

STOI
	Input SNR
Algorithms	−15 dB	−10 dB	−5 dB	0 dB	5 dB
Noisy	0.342	0.418	0.524	0.644	0.758
MMSE-STSA	0.253	0.342	0.471	0.610	0.735
OMLSA	0.265	0.356	0.481	0.614	0.736
GWF-SGS	0.283	0.372	0.506	0.640	0.764
VFGWF	0.255	0.407	0.519	0.645	0.760
GWF-AGS	0.506	0.533	0.567	0.586	0.573
GWF-DCGS	0.520	0.540	0.546	0.527	0.494
GMMSE-KGL	0.315	0.391	0.498	0.603	0.697

Back to article page