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 |
