A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting

09/12/2019

∙

by   Jiancheng Lyu, et al.

∙

0

∙

share

We study channel number reduction in combination with weight binarization (1-bit weight precision) to trim a convolutional neural network for a keyword spotting (classification) task. We adopt a group-wise splitting method based on the group Lasso penalty to achieve over 50 the network performance within 0.25 three-stage procedure to balance accuracy and sparsity in network training.