Skip to main content
Fig. 8 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 8

From: Masked multi-center angular margin loss for language recognition

Fig. 8

Language embeddings of the baselines are plotted by t-SNE, under test-1s on AP17-OLR. Each shape/color represents a different language. a EER=11.35, Cavg=11.05, minDCF=11.09. b EER=10.17, Cavg=9.76, minDCF=10.04. c EER=9.44, Cavg=8.76, minDCF=9.09. d EER=14.23, Cavg=13.56, minDCF=13.73. e EER=13.27, Cavg=12.12, minDCF=12.66. f EER=9.13, Cavg=8.69, minDCF=9.19. g EER=9.05, Cavg=8.54, minDCF=9.01

Back to article page