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

Table 8 Results obtained from different c-vector configurations on VoxCeleb

From: Introducing phonetic information to speaker embedding for speaker verification

 

EER(%)

minDCF08

minDCF10

x-vector

2.68

0.0144

0.4645

c=0.2+ 1-layer sharing

2.18

0.0129

0.2994

c=0.2 + 2-layer sharing

2.32

0.0120

0.3798

c=0.3 + 1-layer sharing

2.33

0.0121

0.3030

c=0.3 + 2-layer sharing

2.24

0.0123

0.3170

Back to article page