Technical Program

Paper Detail

Paper:M1.3
Session:Automatic Speech Recognition I
Location:Earth + Air + Fire
Session Time:Monday, December 14, 11:00 - 12:30
Presentation: Poster
Paper Title: TRAINING DATA PSEUDO-SHUFFLING AND DIRECT DECODING FRAMEWORK FOR RECURRENT NEURAL NETWORK BASED ACOUSTIC MODELING
Authors: Naoyuki Kanda; National Institute of Information and Communications Technology, Japan 
 Mitsuyoshi Tachimori; National Institute of Information and Communications Technology, Japan 
 Xugang Lu; National Institute of Information and Communications Technology, Japan 
 Hisashi Kawai; National Institute of Information and Communications Technology, Japan