Title :
Temporal alignment for deep neural networks
Author :
Payton Lin;Dau-Cheng Lyu;Yun-Fan Chang;Yu Tsao
Author_Institution :
Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan
Abstract :
Alternative features were derived from extracted temporal envelope bank (TBANK). These simplified temporal representations were investigated in alignment procedures to generate frame-level training labels for deep neural networks (DNNs). TBANK features improved temporal alignments both for supervised training and for context dependent tree building.
Keywords :
"Hidden Markov models","Training","Speech","Frequency modulation","Neural networks","Speech recognition","Context"
Conference_Titel :
Signal and Information Processing (GlobalSIP), 2015 IEEE Global Conference on
DOI :
10.1109/GlobalSIP.2015.7418166