Speaker Verification On Voxceleb

المقاييس

EER

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	EER	Paper Title	Repository
ReDimNet-B2-SF2-LM (4.7M)	0.57	Reshape Dimensions Network for Speaker Recognition
WavLM+ECAPA-TDNN	0.39	ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
SimAM-ResNet100	0.20	VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark	-
ReDimNet-B3-LM (3.0M)	0.5	Reshape Dimensions Network for Speaker Recognition
TitanNet -S	1.15	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
ReDimNet-B6-SF2-LM-ASNorm (15.0M)	0.37	Reshape Dimensions Network for Speaker Recognition
SpeechNAS	1.02	SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
ReDimNet-B0-LM-ASNorm (1.0M)	1.07	Reshape Dimensions Network for Speaker Recognition
Multi Task SSL	1.98	Multi-task Voice Activated Framework using Self-supervised Learning	-
ReDimNet-B3-LM-ASNorm (3.0M)	0.47	Reshape Dimensions Network for Speaker Recognition
TitanNet -L	0.68	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
ReDimNet-B0-LM (1.0M)	1.16	Reshape Dimensions Network for Speaker Recognition
ReDimNet-B4-LM-ASNorm (6.3M)	0.44	Reshape Dimensions Network for Speaker Recognition
ReDimNet-B4-LM (6.3M)	0.51	Reshape Dimensions Network for Speaker Recognition
ReDimNet-B5-SF2-LM-ASNorm (9.2M)	0.39	Reshape Dimensions Network for Speaker Recognition
ReDimNet-B6-SF2-LM (15.0M)	0.4	Reshape Dimensions Network for Speaker Recognition
ReDimNet-B1-LM (2.2M)	0.85	Reshape Dimensions Network for Speaker Recognition
TitanNet -M	0.81	TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
ReDimNet-B5-SF2-LM (9.2M)	0.43	Reshape Dimensions Network for Speaker Recognition
ReDimNet-B2-SF2-LM-ASNorm (4.7M)	0.52	Reshape Dimensions Network for Speaker Recognition

0 of 21 row(s) selected.