Beyond cross-entropy: towards better frame-level objective functions for deep neural network training in automatic speech recognition

Zhen Huang, Jinyu Li, Chao Weng, Chin-Hui Lee. Beyond cross-entropy: towards better frame-level objective functions for deep neural network training in automatic speech recognition. In Haizhou Li, Helen M. Meng, Bin Ma, Eng Siong Chng, Lei Xie, editors, INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014. pages 1214-1218, ISCA, 2014. [doi]

Abstract

Abstract is missing.