most citedMarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection

5 citations · 5 across the 1 of their papers we have counts for

collaborators

1 paper

eess.AS2020★ 5 cited

MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection

Fei Jia, Somshubra Majumdar, Boris Ginsburg

We present MarbleNet, an end-to-end neural network for Voice Activity Detection (VAD). MarbleNet is a deep residual network composed from blocks of 1D time-channel separable convol…