HyperAI超神経

プラットフォーム

Speaker Diarization On Nist Sre 2000

評価指標

DER(%)

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
x-vector (PLDA + AHC)	8.39	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
TitaNet-L (NME-SC)	6.73	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
TitaNet-M (NME-SC)	6.47	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
TitaNet-S (NME-SC)	6.37	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
x-vector (MCGAN)	5.73	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context

0 of 5 row(s) selected.