HyperAIHyperAI초신경

Command Palette

Search for a command to run...

플랫폼

Speaker Verification On Voxceleb

평가 지표

EER

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper Title
Multi Task SSL1.98Multi-task Voice Activated Framework using Self-supervised Learning
ReDimNet-B0-LM (1.0M)1.16Reshape Dimensions Network for Speaker Recognition
TitanNet -S1.15TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
ReDimNet-B0-LM-ASNorm (1.0M)1.07Reshape Dimensions Network for Speaker Recognition
SpeechNAS1.02SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
ReDimNet-B1-LM (2.2M)0.85Reshape Dimensions Network for Speaker Recognition
TitanNet -M0.81TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
ReDimNet-B1-LM-ASNorm (2.2M)0.73Reshape Dimensions Network for Speaker Recognition
TitanNet -L0.68TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
ReDimNet-B2-SF2-LM (4.7M)0.57Reshape Dimensions Network for Speaker Recognition
ReDimNet-B2-SF2-LM-ASNorm (4.7M)0.52Reshape Dimensions Network for Speaker Recognition
ReDimNet-B4-LM (6.3M)0.51Reshape Dimensions Network for Speaker Recognition
ReDimNet-B3-LM (3.0M)0.5Reshape Dimensions Network for Speaker Recognition
ReDimNet-B3-LM-ASNorm (3.0M)0.47Reshape Dimensions Network for Speaker Recognition
ReDimNet-B4-LM-ASNorm (6.3M)0.44Reshape Dimensions Network for Speaker Recognition
ReDimNet-B5-SF2-LM (9.2M)0.43Reshape Dimensions Network for Speaker Recognition
ReDimNet-B6-SF2-LM (15.0M)0.4Reshape Dimensions Network for Speaker Recognition
WavLM+ECAPA-TDNN0.39ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
ReDimNet-B5-SF2-LM-ASNorm (9.2M)0.39Reshape Dimensions Network for Speaker Recognition
ReDimNet-B6-SF2-LM-ASNorm (15.0M)0.37Reshape Dimensions Network for Speaker Recognition
0 of 21 row(s) selected.