Skip to main content

Table 8 Comparison with some known systems based on hand-crafted features on the ASVspoof 2017 V2 evaluation set in terms of EER(%)

From: Discriminative features based on modified log magnitude spectrum for playback speech detection

FeatureClassifierEER
CQCC-SDA [30]GMM15.33
(CQCC-logE)-SDA [30]GMM12.24
CQCC-SDA [30]I-vector15.63
(CQCC-logE)-SDA [30]I-vector12.93
qDFTspe [42]GMM11.19
CQCC-SDADNN32.46
CQCC-DADNN15.18
CMPOC-DA [40]DNN14.99
CMPOC-D [40]DNN14.93
eCQCC-DA [38]DNN13.38
CQSPIC-DA [41]DNN11.09
CMOC-DADNN14.16
CVOC-DADNN11.46