Technical Program

ASR.1: Automatic Speech Recognition I

Session Type: Poster
Poster Time: Sunday, December 17, 11:00 - 12:30
Location: Poster Area
Session Chair: Shinji Watanabe, Johns Hopkins University
 
ASR.1.1: REDUCING THE COMPUTATIONAL COMPLEXITY FOR WHOLE WORD MODELS
         Hagen Soltau; Google Inc., United States
         Hank Liao; Google Inc., United States
         Hasim Sak; Google Inc., United States
 
ASR.1.2: INVESTIGATION OF LATTICE-FREE MAXIMUM MUTUAL INFORMATION-BASED ACOUSTIC MODELS WITH SEQUENCE-LEVEL KULLBACK-LEIBLER DIVERGENCE
         Naoyuki Kanda; Hitachi Ltd., Japan
         Yusuke Fujita; Hitachi Ltd., Japan
         Kenji Nagamatsu; Hitachi Ltd., Japan
 
ASR.1.3: SEMI-SUPERVISED TRAINING STRATEGIES FOR DEEP NEURAL NETWORKS
         Matthew Gibson; Nuance Communications Inc., United Kingdom
         Gary Cook; Nuance Communications Inc., United Kingdom
         Puming Zhan; Nuance Communications Inc., United States
 
ASR.1.4: MULTI-TASK ENSEMBLES WITH TEACHER-STUDENT TRAINING
         Jeremy Heng Meng Wong; University of Cambridge, United Kingdom
         Mark J. F. Gales; University of Cambridge, United Kingdom
 
ASR.1.5: LANGUAGE DIARIZATION FOR SEMI-SUPERVISED BILINGUAL ACOUSTIC MODEL TRAINING
         Emre Yilmaz; Radboud University, Netherlands
         Mitchell McLaren; SRI International, United States
         Henk van den Heuvel; Radboud University, Netherlands
         David A. van Leeuwen; Radboud University, Netherlands
 
ASR.1.6: FUTURE WORD CONTEXTS IN NEURAL NETWORK LANGUAGE MODELS
         Xie Chen; University of Cambridge, United Kingdom
         Xunying Liu; Chinese University of Hong Kong, China
         Anton Ragni; University of Cambridge, United Kingdom
         Yu Wang; University of Cambridge, United Kingdom
         Mark J. F. Gales; University of Cambridge, United Kingdom
 
ASR.1.7: FUTURE VECTOR ENHANCED LSTM LANGUAGE MODEL FOR LVCSR
         Qi Liu; Shanghai Jiao Tong University, China
         Yanmin Qian; Shanghai Jiao Tong University, China
         Kai Yu; Shanghai Jiao Tong University, China
 
ASR.1.8: ACOUSTIC-TO-WORD MODEL WITHOUT OOV
         Jinyu Li; Microsoft, United States
         Guoli Ye; Microsoft, United States
         Rui Zhao; Microsoft, United States
         Jasha Droppo; Microsoft, United States
         Yifan Gong; Microsoft, United States
 
ASR.1.9: TURBO FUSION OF MAGNITUDE AND PHASE INFORMATION FOR DNN-BASED PHONEME RECOGNITION
         Timo Lohrenz; TU Braunschweig, Germany
         Tim Fingscheidt; TU Braunschweig, Germany
 
ASR.1.10: COMPUTATIONAL COST REDUCTION OF LONG SHORT-TERM MEMORY BASED ON SIMULTANEOUS COMPRESSION OF INPUT AND HIDDEN STATE
         Takashi Masuko; Toshiba Corporation, Japan
 
ASR.1.11: CROSS-DOMAIN SPEECH RECOGNITION USING NONPARALLEL CORPORA WITH CYCLE-CONSISTENT ADVERSARIAL NETWORKS
         Masato Mimura; Kyoto University, Japan
         Shinsuke Sakai; Kyoto University, Japan
         Tatsuya Kawahara; Kyoto University, Japan
 
ASR.1.12: WERD: USING SOCIAL TEXT SPELLING VARIANTS FOR EVALUATING DIALECTAL SPEECH RECOGNITION
         Ahmed Ali; Qatar Computing Research Institute, Qatar
         Preslav Nakov; Qatar Computing Research Institute, Qatar
         Peter Bell; University of Edinburgh, United Kingdom
         Steve Renals; University of Edinburgh, United Kingdom
 
ASR.1.13: CHARACTER-BASED UNITS FOR UNLIMITED VOCABULARY CONTINUOUS SPEECH RECOGNITION
         Peter Smit; Aalto University, Finland
         Siva Reddy Gangireddy; Aalto University, Finland
         Seppo Enarvi; Aalto University, Finland
         Sami Virpioja; Aalto University, Finland
         Mikko Kurimo; Aalto University, Finland
 
ASR.1.14: GATED CONVOLUTIONAL NETWORKS BASED HYBRID ACOUSTIC MODELS FOR LOW RESOURCE SPEECH RECOGNITION
         Jian Kang; Tsinghua university, China
         Wei-Qiang Zhang; Tsinghua university, China
         Jia Liu; Tsinghua university, China
 
ASR.1.15: LATTICE RESCORING STRATEGIES FOR LONG SHORT TERM MEMORY LANGUAGE MODELS IN SPEECH RECOGNITION
         Shankar Kumar; Google Inc., United States
         Michael Nirschl; Google Inc., United States
         Daniel Holtmann-Rice; Google Inc., United States
         Hank Liao; Google Inc., United States
         Ananda Theertha Suresh; Google Inc., United States
         Felix Yu; Google Inc., United States
 
ASR.1.16: SYLLABLE-BASED ACOUSTIC MODELING WITH CTC-SMBR-LSTM
         Zhongdi Qu; Google Inc., United States
         Parisa Haghani; Google Inc., United States
         Eugene Weinstein; Google Inc., United States
         Pedro Moreno; Google Inc., United States
 
ASR.1.17: SEQUENCE TRAINING OF DNN ACOUSTIC MODELS WITH NATURAL GRADIENT
         Adnan Haider; University of Cambridge, United Kingdom
         Philip Woodland; University of Cambridge, United Kingdom
 
ASR.1.18: CONSISTENT DNN UNCERTAINTY TRAINING AND DECODING FOR ROBUST ASR
         Karan Nathwani; INRIA, Nancy, France
         Emmanuel Vincent; INRIA, Nancy, France
         Irina Illina; INRIA-LORIA, Nancy, France
 

Sponsors

Technical Sponsor