Login Paper Search My Schedule Paper Index Help

My ICASSP 2019 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.

SLP-P11: ASR Training Strategies and Toolkits

Session Type: Poster
Time: Thursday, May 16, 08:00 - 10:00
Location: Poster Area A, Ground Floor
Session Chair: Erik McDermott, Google, Inc.
 
  SLP-P11.1: TEACH AN ALL-ROUNDER WITH EXPERTS IN DIFFERENT DOMAINS
         Zhao You; Tencent
         Dan Su; Tencent
         Dong Yu; Tencent
 
  SLP-P11.2: A COMPARISON OF LATTICE-FREE DISCRIMINATIVE TRAINING CRITERIA FOR PURELY SEQUENCE-TRAINED NEURAL NETWORK ACOUSTIC MODELS
         Chao Weng; Tencent
         Dong Yu; Tencent
 
  SLP-P11.3: SEGMENT-LEVEL TRAINING OF ANNS BASED ON ACOUSTIC CONFIDENCE MEASURES FOR HYBRID HMM/ANN SPEECH RECOGNITION
         S. Pavankumar Dubagunta; Idiap Research Institute
         Mathew Magimai.-Doss; Idiap Research Institute
 
  SLP-P11.4: CONTEXTUAL SPEECH RECOGNITION WITH DIFFICULT NEGATIVE TRAINING EXAMPLES
         Uri Alon; Technion
         Golan Pundak; Google, Inc.
         Tara N. Sainath; Google, Inc.
 
  SLP-P11.5: CONDITIONAL TEACHER-STUDENT LEARNING
         Zhong Meng; Microsoft Corporation
         Jinyu Li; Microsoft Corporation
         Yong Zhao; Microsoft Corporation
         Yifan Gong; Microsoft Corporation
 
  SLP-P11.6: A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED
         Zhengyu Zhou; Bosch Research and Technology Center North America
         Xuchen Song; Carnegie Mellon University
         Rami Botros; Google, Inc.
         Lin Zhao; Bosch Research and Technology Center North America
 
  SLP-P11.7: ENGLISH BROADCAST NEWS SPEECH RECOGNITION BY HUMANS AND MACHINES
         Samuel Thomas; IBM Research
         Masayuki Suzuki; IBM Research
         Yinghui Huang; IBM Research
         Gakuto Kurata; IBM Research
         Zoltan Tuske; IBM Research
         George Saon; IBM Research
         Brian Kingsbury; IBM Research
         Michael Picheny; IBM Research
         Tom Dibert; Appen
         Alice Kaiser-Schatzlein; Appen
         Bern Samko; Appen
 
  SLP-P11.8: WAV2LETTER++: A FAST OPEN-SOURCE SPEECH RECOGNITION SYSTEM
         Vineel Pratap; Facebook AI Research
         Awni Hannun; Facebook AI Research
         Qiantong Xu; Facebook AI Research
         Jeff Cai; Facebook AI Research
         Jacob Kahn; Facebook AI Research
         Gabriel Synnaeve; Facebook AI Research
         Vitaliy Liptchinsky; Facebook AI Research
         Ronan Collobert; Facebook AI Research
 
  SLP-P11.9: THE PYTORCH-KALDI SPEECH RECOGNITION TOOLKIT
         Mirco Ravanelli; Mila, Université de Montréal
         Titouan Parcollet; Université d'Avignon
         Yoshua Bengio; Mila, Université de Montréal
 
  SLP-P11.10: PYHTK: PYTHON LIBRARY AND ASR PIPELINES FOR HTK
         Chao Zhang; University of Cambridge
         Florian Kreyssig; University of Cambridge
         Qiujia Li; University of Cambridge
         Philip Woodland; University of Cambridge
 
  SLP-P11.11: IMPROVING NOISE ROBUSTNESS OF AUTOMATIC SPEECH RECOGNITION VIA PARALLEL DATA AND TEACHER-STUDENT LEARNING
         Ladislav Mosner; Brno University of Technology
         Minhua Wu; Amazon
         Anirudh Raju; Amazon
         Sree Hari Krishnan Parthasarathi; Amazon
         Kenichi Kumatani; Amazon
         Shiva Sundaram; Amazon
         Roland Maas; Amazon
         Björn Hoffmeister; Amazon