Skip to main content

Table 2 Performance of relative SVM supervector reconstruction subsystem, TFLLR and RBF kernel

From: Homogenous ensemble phonotactic language recognition based on SVM supervector reconstruction

 

30 s

10 s

3 s

 

EER

Cavg

EER

Cavg

EER

Cavg

HU

2.38

2.40

7.11

7.17

20.32

20.49

RU

2.01

1.92

5.83

5.77

17.26

17.34

CZ

3.14

3.09

8.47

8.53

23.12

23.17

  1. NIST LRE 2009 (EER and Cavg in percent).