Technical Program

SP-P5: Acoustic Modeling I

Session Type: Poster
Time: Tuesday, March 7, 13:30 - 15:30
Location: Churchill: Poster Area A
Session Chair: Kartik Audhkhasi, IBM T. J. Watson Research Center
 
SP-P5.1: THE MICROSOFT 2016 CONVERSATIONAL SPEECH RECOGNITION SYSTEM
         Wayne Xiong; Microsoft
         Jasha Droppo; Microsoft
         Xuedong Huang; Microsoft
         Frank Seide; Microsoft
         Michael L. Seltzer; Microsoft
         Andreas Stolcke; Microsoft
         Dong Yu; Microsoft
         Geoffrey Zweig; Microsoft
 
SP-P5.2: PARALLEL PHONETICALLY AWARE DNNS AND LSTM-RNNS FOR FRAME-BY-FRAME DISCRIMINATIVE MODELING OF SPOKEN LANGUAGE IDENTIFICATION
         Ryo Masumura; NTT Corporation
         Taichi Asami; NTT Corporation
         Hirokazu Masataki; NTT Corporation
         Yushi Aono; NTT Corporation
 
SP-P5.3: LOW-RANK AND SPARSE SOFT TARGETS TO LEARN BETTER DNN ACOUSTIC MODELS
         Pranay Dighe; IDIAP/EPFL
         Afsaneh Asaei; Idiap Research Institute
         Herve Bourlard; IDIAP/EPFL
 
SP-P5.4: SEMI-SUPERVISED ENSEMBLE DNN ACOUSTIC MODEL TRAINING
         Sheng Li; School of Informatics, Kyoto University
         Xugang Lu; National Institute of Information and Communications Technology
         Shinsuke Sakai; School of Informatics, Kyoto University
         Masato Mimura; School of Informatics, Kyoto University
         Tatsuya Kawahara; School of Informatics, Kyoto University
 
SP-P5.5: STUDENT-TEACHER NETWORK LEARNING WITH ENHANCED FEATURES
         Shinji Watanabe; Mitsubishi Electric Research Laboratories
         Takaaki Hori; Mitsubishi Electric Research Laboratories
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories
         John R. Hershey; Mitsubishi Electric Research Laboratories
 
SP-P5.6: END-TO-END SPEECH RECOGNITION AND KEYWORD SEARCH ON LOW-RESOURCE LANGUAGES
         Andrew Rosenberg; IBM
         Kartik Audhkhasi; IBM
         Abhinav Sethy; IBM
         Bhuvana Ramabhadran; IBM
         Michael Picheny; IBM
 
SP-P5.7: FASTER SEQUENCE TRAINING
         Albert Zeyer; RWTH Aachen University
         Ilia Kulikov; RWTH Aachen University
         Ralf Schl├╝ter; RWTH Aachen University
         Hermann Ney; RWTH Aachen University
 
SP-P5.8: ALTERNATIVE NETWORKS FOR MONOLINGUAL BOTTLENECK FEATURES
         William Hartmann; Raytheon BBN Technologies
         Roger Hsiao; Raytheon BBN Technologies
         Stavros Tsakalidis; Raytheon BBN Technologies
 
SP-P5.9: NETWORK ARCHITECTURES FOR MULTILINGUAL SPEECH REPRESENTATION LEARNING
         Tom Sercu; IBM T.J. Watson Research Center
         George Saon; IBM T.J. Watson Research Center
         Jia Cui; IBM T.J. Watson Research Center
         Xiadong Cui; IBM T.J. Watson Research Center
         Bhuvana Ramabhadran; IBM T.J. Watson Research Center
         Brian Kingsbury; IBM T.J. Watson Research Center
         Abhinav Sethy; IBM T.J. Watson Research Center
 
SP-P5.10: RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING
         Yue Zhao; Tsinghua University
         Xingyu Jin; Tsinghua University
         Xiaolin Hu; Tsinghua University