Fig. 11From: Masked multi-center angular margin loss for language recognitionLanguage embeddings of our proposed method are plotted by t-SNE, under test-all on AP17-OLR. Each shape/color represents a different language. a EER=1.44, Cavg=1.31, minDCF=1.36. b EER=1.39, Cavg=1.39, minDCF=1.41. c EER=1.35, Cavg=1.23, minDCF=1.31Back to article page