Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 7 Comparison with existing spoofing detection systems

From: DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection

Model

Logical access

Dev

Eval

FFT-L-SENet [70]

-

1.14

Attention-based CNN [71]

0.16

1.87

LFCC-PC-DARTS [72]

0.002

4.87

RAWNet2 [73]

-

1.12

W2V-Siamese [74]

0.004

1.15

W2V2-light-DARTS [75]

0.02

1.08

EDL-Det [76]

0.80

0.045

DeepDet

0.015

0.042

Back to article page