Table 3.

Result of models used in perception branch and input features on ASVspoof 2019 evaluation dataset for PA and LA scenarios. K, M, and G represent Kilo, Mega, and Giga, respectively

#	Perception branch model	Input feature	#Parameters	#Flops	PA		LA
					EER(%)	t-DCF	EER(%)	t-DCF
1	EfficientNet-A0	LFCC	95k	198 M	–	–	3.68	0.0931
2	EfficientNet-A0	LogPowSepc		1.696 G	0.86	0.0239	–	–
3	SE-Res2Net50	LFCC	964k	1.519 G	–	–	1.89	0.0597
4	SE-Res2Net50	LogPowSepc		12.929 G	0.98	0.2769	–	–