ASR.2: Automatic Speech Recognition II |
| Session Type: Poster |
| Poster Time: Monday, December 18, 15:30 - 17:00 |
| Location: Poster Area |
| Session Chair: Thomas Hain, University of Sheffield |
| ASR.2.1: EXPLORING ARCHITECTURES, DATA AND UNITS FOR STREAMING END-TO-END SPEECH RECOGNITION WITH RNN-TRANSDUCER |
| Kanishka Rao; Google Inc., United States |
| Hasim Sak; Google Inc., United States |
| Rohit Prabhavalkar; Google Inc., United States |
| ASR.2.2: UNSUPERVISED ADAPTATION OF STUDENT DNNS LEARNED FROM TEACHER RNNS FOR IMPROVED ASR PERFORMANCE |
| Lahiru Samarakoon; Hong Kong University of Science and Technology, China |
| Brian Mak; Hong Kong University of Science and Technology, China |
| ASR.2.3: EXPLORING NEURAL TRANSDUCERS FOR END-TO-END SPEECH RECOGNITION |
| Eric Battenberg; Baidu SVAIL, United States |
| Jitong Chen; Baidu SVAIL, United States |
| Rewon Child; Baidu SVAIL, United States |
| Adam Coates; Baidu SVAIL, United States |
| Yashesh Gaur; Baidu SVAIL, United States |
| Yi Li; Baidu SVAIL, United States |
| Hairong Liu; Baidu SVAIL, United States |
| Sanjeev Satheesh; Baidu SVAIL, United States |
| Anuroop Sriram; Baidu SVAIL, United States |
| Zhenyao Zhu; Baidu SVAIL, United States |
| ASR.2.4: UNSUPERVISED ADAPTATION WITH DOMAIN SEPARATION NETWORKS FOR ROBUST SPEECH RECOGNITION |
| Zhong Meng; Georgia Institute of Technology, United States |
| Zhuo Chen; Microsoft Corporation, United States |
| Vadim Mazalov; Microsoft Corporation, United States |
| Jinyu Li; Microsoft Corporation, United States |
| Yifan Gong; Microsoft Corporation, United States |
| ASR.2.5: INCREMENTAL TRAINING AND CONSTRUCTING THE VERY DEEP CONVOLUTIONAL RESIDUAL NETWORK ACOUSTIC MODELS |
| Sheng Li; National Institute of Information and Communications Technology, Japan |
| Xugang Lu; National Institute of Information and Communications Technology, Japan |
| Peng Shen; National Institute of Information and Communications Technology, Japan |
| Ryoichi Takashima; National Institute of Information and Communications Technology, Japan |
| Tatsuya Kawahara; Kyoto University, Japan |
| Hisashi Kawai; National Institute of Information and Communications Technology, Japan |
| ASR.2.6: ON LATTICE GENERATION FOR LARGE VOCABULARY SPEECH RECOGNITION |
| David Rybach; Google Inc., Germany |
| Michael Riley; Google Inc., United States |
| Johan Schalkwyk; Google Inc., United States |
| ASR.2.7: SIMPLIFYING VERY DEEP CONVOLUTIONAL NEURAL NETWORK ARCHITECTURES FOR ROBUST SPEECH RECOGNITION |
| Joanna Rownicka; University of Edinburgh, United Kingdom |
| Steve Renals; University of Edinburgh, United Kingdom |
| Peter Bell; University of Edinburgh, United Kingdom |
| ASR.2.8: LANGUAGE MODELING WITH HIGHWAY LSTM |
| Gakuto Kurata; IBM Research, Japan |
| Bhuvana Ramabhadran; IBM Research, United States |
| George Saon; IBM Research, United States |
| Abhinav Sethy; IBM Research, United States |
| ASR.2.9: DIRECT MODELING OF RAW AUDIO WITH DNNS FOR WAKE WORD DETECTION |
| Kenichi Kumatani; Amazon Inc., United States |
| Sankaran Panchapagesan; Amazon Inc., United States |
| Minhua Wu; Amazon Inc., United States |
| Minjae Kim; Amazon Inc., United States |
| Nikko Strom; Amazon Inc., United States |
| Gautam Tiwari; Amazon Inc., United States |
| Arindam Mandal; Amazon Inc., United States |
| ASR.2.10: IMPROVING THE EFFICIENCY OF FORWARD-BACKWARD ALGORITHM USING BATCHED COMPUTATION IN TENSORFLOW |
| Khe Chai Sim; Google Inc., United States |
| Arun Narayanan; Google Inc., United States |
| Tom Bagby; Google Inc., United States |
| Tara Sainath; Google Inc., United States |
| Michiel Bacchiani; Google Inc., United States |
| ASR.2.11: LANGUAGE INDEPENDENT END-TO-END ARCHITECTURE FOR JOINT LANGUAGE IDENTIFICATION AND SPEECH RECOGNITION |
| Shinji Watanabe; Johns Hopkins University, United States |
| Takaaki Hori; Mitsubishi Electric Research Laboratories, United States |
| John Hershey; Mitsubishi Electric Research Laboratories, United States |
| ASR.2.12: KEYWORD SPOTTING FOR GOOGLE ASSISTANT USING CONTEXTUAL SPEECH RECOGNITION |
| Assaf Hurwitz Michaely; Google Inc., United States |
| Xuedong Zhang; Google Inc., United States |
| Gabor Simko; Google Inc., United States |
| Carolina Parada; Google Inc., United States |
| Petar Aleksic; Google Inc., United States |
| ASR.2.13: INVESTIGATION OF TRANSFER LEARNING FOR ASR USING LF-MMI TRAINED NEURAL NETWORKS |
| Pegah Ghahremani; Johns Hopkins University, United States |
| Vimal Manohar; Johns Hopkins University, United States |
| Hossein Hadian; Johns Hopkins University, United States |
| Daniel Povey; Johns Hopkins University, United States |
| Sanjeev Khudanpur; Johns Hopkins University, United States |
| ASR.2.14: MULTI-LEVEL LANGUAGE MODELING AND DECODING FOR OPEN VOCABULARY END-TO-END SPEECH RECOGNITION |
| Takaaki Hori; Mitsubishi Electric Research Laboratories, United States |
| Shinji Watanabe; Johns Hopkins University, United States |
| John Hershey; Mitsubishi Electric Research Laboratories, United States |
| ASR.2.15: LANGUAGE MODELING WITH NEURAL TRANS-DIMENSIONAL RANDOM FIELDS |
| Bin Wang; Tsinghua university, China |
| Zhijian Ou; Tsinghua university, China |
| ASR.2.16: LISTENING WHILE SPEAKING: SPEECH CHAIN BY DEEP LEARNING |
| Andros Tjandra; Nara Institute of Science and Technology, Japan |
| Sakriani Sakti; Nara Institute of Science and Technology, Japan |
| Satoshi Nakamura; Nara Institute of Science and Technology, Japan |
| ASR.2.17: ATTENTION-BASED WAV2TEXT WITH FEATURE TRANSFER LEARNING |
| Andros Tjandra; Nara Institute of Science and Technology, Japan |
| Sakriani Sakti; Nara Institute of Science and Technology, Japan |
| Satoshi Nakamura; Nara Institute of Science and Technology, Japan |
