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

Table 4 Phonetic adaptation results on VoxCeleb

From: Introducing phonetic information to speaker embedding for speaker verification

 

EER(%)

minDCF08

minDCF10

x-vector

2.68

0.0144

0.4645

x-vector-pa (c=0)

2.52

0.0137

0.4111

x-vector-pa (c=0.1)

2.26

0.0126

0.3651

x-vector-pa (c=0.2)

2.24

0.0132

0.3289

x-vector-pa (c=0.3)

2.32

0.0124

0.3533

x-vector-pa (c=0.4)

2.32

0.0126

0.3531

Back to article page