Technical Program
SP-L1: Neural Network Trends in Speech Recognition |
Session Type: Lecture |
Time: Monday, March 6, 13:30 - 15:30 |
Location: Grand Ballroom |
Session Chairs: Tara Sainath, Google and Yifan Gong, Microsoft |
SP-L1.1: ADVANCES IN ALL-NEURAL SPEECH RECOGNITION |
Geoffrey Zweig; Microsoft |
Chengzhu Yu; The University of Texas at Dallas |
Jasha Droppo; Microsoft |
Andreas Stolcke; Microsoft |
SP-L1.2: RESIDUAL MEMORY NETWORKS: FEED-FORWARD APPROACH TO LEARN LONG-TERM TEMPORAL DEPENDENCIES |
Murali Karthick Baskar; Brno University of Technology |
Martin Karafi´at; Brno University of Technology |
Lukas Burget; Brno University of Technology |
Karel Vesel´y; Brno University of Technology |
Frantiˇsek Gr´ezl; Brno University of Technology |
Jan “honza” Cernocky; Brno University of Technology |
SP-L1.3: MULTI-ACCENT SPEECH RECOGNITION WITH HIERARCHICAL GRAPHEME BASED MODELS |
Kanishka Rao; Google Inc. |
Hasim Sak; Google Inc. |
SP-L1.4: KNOWLEDGE DISTILLATION FOR SMALL-FOOTPRINT HIGHWAY NETWORKS |
Liang Lu; Toyota Technological Institute at Chicago |
Michelle Guo; Stanford University |
Steve Renals; The University of Edinburgh |
SP-L1.5: KNOWLEDGE DISTILLATION ACROSS ENSEMBLES OF MULTILINGUAL MODELS FOR LOW-RESOURCE LANGUAGES |
Jia Cui; IBM T.J. Watson Research Center |
Brian Kingsbury; IBM T.J. Watson Research Center |
Bhuvana Ramabhadran; IBM T.J. Watson Research Center |
George Saon; IBM T.J. Watson Research Center |
Tom Sercu; IBM T.J. Watson Research Center |
Kartik Audhkhasi; IBM T.J. Watson Research Center |
Abhinav Sethy; IBM T.J. Watson Research Center |
Markus Nussbaum-Thom; IBM T.J. Watson Research Center |
Andrew Rosenberg; IBM T.J. Watson Research Center |
SP-L1.6: STIMULATED TRAINING FOR AUTOMATIC SPEECH RECOGNITION AND KEYWORD SEARCH IN LIMITED RESOURCE CONDITIONS |
Anton Ragni; University of Cambridge |
Chunyang Wu; University of Cambridge |
Mark Gales; University of Cambridge |
Jake Vasilakes; University of Cambridge |
Kate Knill; University of Cambridge |