Acoustic model training based on node-wise weight boundary model increasing speed of discrete neural networks

Ryu Takeda, Kazunori Komatani, Kazuhiro Nakadai. Acoustic model training based on node-wise weight boundary model increasing speed of discrete neural networks. In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015. pages 52-58, IEEE, 2015. [doi]

Abstract

Abstract is missing.