Fig. 9From: Masked multi-center angular margin loss for language recognitionLanguage embeddings of our proposed method are plotted by t-SNE, under test-1s on AP17-OLR. Each shape/color represents a different language. a EER=8.42, Cavg=7.93, minDCF=8.12. b EER=8.16, Cavg=7.60, minDCF=7.30. c EER=7.78, Cavg=7.28, minDCF=7.63Back to article page