Ran Lee

NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification

In speaker verification, ECAPA-TDNN has shown remarkable improvement by utilizing one-dimensional(1D) Res2Net block and squeeze-and-excitation(SE) module, along with multi-layer feature aggregation (MFA). Meanwhile, in vision tasks, ConvNet structures have been modernized by referring to Transformer…