Skip to main content
Fig. 10 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 10

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

Fig. 10

Language embeddings of the baselines are plotted by t-SNE, under test-all on AP17-OLR. Each shape/color represents a different language. a EER=4.15, Cavg=3.89, minDCF=3.92. b EER=1.83, Cavg=1.79, minDCF=1.92. c EER=2.16, Cavg=1.98, minDCF=2.01. d EER=3.60, Cavg=3.51, minDCF=3.61. e EER=3.43, Cavg=3.26, minDCF=3.33. f EER=2.02, Cavg=1.84, minDCF=2.12. g EER=2.03, Cavg=1.87, minDCF=2.02

Back to article page