Technical Program

Paper Detail

Paper:SP-P5.9
Session:Acoustic Modeling I
Location:Churchill: Poster Area A
Session Time:Tuesday, March 7, 13:30 - 15:30
Presentation Time:Tuesday, March 7, 13:30 - 15:30
Presentation: Poster
Topic: Speech Processing: Acoustic Modeling for Automatic Speech Recognition
Paper Title: NETWORK ARCHITECTURES FOR MULTILINGUAL SPEECH REPRESENTATION LEARNING
Authors: Tom Sercu, George Saon, Jia Cui, Xiadong Cui, Bhuvana Ramabhadran, Brian Kingsbury, Abhinav Sethy, IBM T.J. Watson Research Center, United States