Login Paper Search My Schedule Paper Index Help

My SLT 2018 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Clicking on the Add button next to a paper title will add that paper to your custom schedule.
Clicking on the Remove button next to a paper will remove that paper from your custom schedule.

ASR III (End-to-End)

Session Type: Poster
Time: Friday, December 21, 10:00 - 12:00
Location: Kallirhoe Hall
 
  1: IMPROVING ATTENTION-BASED END-TO-END ASR SYSTEMS WITH SEQUENCE-BASED LOSS FUNCTIONS
         Jia Cui; Tencent AI Lab
         Chao Weng; Tencent AI Lab
         Guangsen Wang; Tencent AI Lab
         Jun Wang; Tencent AI Lab
         Peidong Wang; The Ohio State University
         Chengzhu Yu; Tencent AI Lab
         Dan Su; Tencent AI Lab
         Dong Yu; Tencent AI Lab
 
  2: COMBINING END-TO-END AND ADVERSARIAL TRAINING FOR LOW-RESOURCE SPEECH RECOGNITION
         Jennifer Drexler; Massachusetts Institute of Technology
         James Glass; Massachusetts Institute of Technology
 
  3: A COMPARISON OF TECHNIQUES FOR LANGUAGE MODEL INTEGRATION IN ENCODER-DECODER SPEECH RECOGNITION
         Shubham Toshniwal; Toyota Technological Institute at Chicago
         Anjuli Kannan; Google
         Chung-Cheng Chiu; Google
         Yonghui Wu; Google
         Tara N. Sainath; Google
         Karen Livescu; Toyota Technological Institute at Chicago
 
  4: ON-DEVICE END-TO-END SPEECH RECOGNITION WITH MULTI-STEP PARALLEL RNNS
         Yoonho Boo; Seoul National University
         Jinhwan Park; Seoul National University
         Lukas Lee; Seoul National University
         Wonyong Sung; Seoul National University
 
  5: DOMAIN ADAPTATION OF END-TO-END SPEECH RECOGNITION IN LOW-RESOURCE SETTINGS
         Lahiru Samarakoon; Fano Labs
         Brian Mak; Hong Kong University of Science and Technology
         Albert Lam; Fano Labs
 
  6: END-TO-END SPEECH RECOGNITION WITH WORD-BASED RNN LANGUAGE MODELS
         Takaaki Hori; Mitsubishi Electric Research Laboratories
         Jaejin Cho; Johns Hopkins University
         Shinji Watanabe; Johns Hopkins University
 
  7: ACOUSTIC-TO-WORD RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODELS
         Shruti Palaskar; Carnegie Mellon University
         Florian Metze; Carnegie Mellon University
 
  8: COMBINING DE-NOISING AUTO-ENCODER AND RECURRENT NEURAL NETWORKS IN END-TO-END AUTOMATIC SPEECH RECOGNITION FOR NOISE ROBUSTNESS
         Tzu-Hsuan Ting; National Sun Yat-sen University
         Chia-Ping Chen; National Sun Yat-sen University
 
  9: IMPROVED KNOWLEDGE DISTILLATION FROM BI-DIRECTIONAL TO UNI-DIRECTIONAL LSTM CTC FOR END-TO-END SPEECH RECOGNITION
         Gakuto Kurata; IBM Research
         Kartik Audhkhasi; IBM Research
 
  10: DEEP CONTEXT: END-TO-END CONTEXTUAL SPEECH RECOGNITION
         Golan Pundak; Google
         Tara N. Sainath; Google
         Rohit Prabhavalkar; Google
         Anjuli Kannan; Google
         Ding Zhao; Google
 
  11: BACK-TRANSLATION-STYLE DATA AUGMENTATION FOR END-TO-END ASR
         Tomoki Hayashi; Nagoya University
         Shinji Watanabe; Johns Hopkins University
         Yu Zhang; Google
         Tomoki Toda; Nagoya University
         Takaaki Hori; Mitsubishi Electric Research Laboratories
         Ramon Astudillo; INESC-ID-Lisboa
         Kazuya Takeda; Nagoya University
 
  12: DIALOG-CONTEXT AWARE END-TO-END SPEECH RECOGNITION
         Suyoun Kim; Carnegie Mellon University
         Florian Metze; Carnegie Mellon University