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 Schlüter; 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 |