Skip to main content

Table 6 The comparison of our best model with the best two-stage model and the top three models on the OLR20 challenge

From: Three-stage training and orthogonality regularization for spoken language recognition

ID

Model

\(\lambda\)

channel-test

noisy-test

   

Cavg%

EER%

Cavg%

EER%

0

Top 1 on the OLR20 Challenge [51]

-

2.39

2.47

3.47

4.07

1

Top 2 on the OLR20 Challenge [51]

-

4.21

4.51

4.76

4.87

2

Top 3 on the OLR20 Challenge [51]

-

4.77

4.82

5.38

5.60

3

The best two-stage model

0.1

3.90

7.25

2.06

4.20

4

The best three-stage model (ours)

0.1

1.88

3.57

1.86

3.74