SLP-L1: End-to-end Speech Recognition I: General Topics |
Session Type: Lecture |
Time: Tuesday, May 14, 13:30 - 15:30 |
Location: Auditorium 1 |
Session Chairs: Bhuvana Ramabhadran, Google Inc. and Shinji Watanabe, The Johns Hopkins University
|
|
SLP-L1.1: BYTES ARE ALL YOU NEED: END-TO-END MULTILINGUAL SPEECH RECOGNITION AND SYNTHESIS WITH BYTES |
Bo Li; Google, Inc. |
Yu Zhang; Google, Inc. |
Tara N. Sainath; Google, Inc. |
Yonghui Wu; Google, Inc. |
William Chan; Google, Inc. |
|
SLP-L1.2: JOINT ENDPOINTING AND DECODING WITH END-TO-END MODELS |
Shuo-yiin Chang; Google, Inc. |
Rohit Prabhavalkar; Google, Inc. |
Yanzhang He; Google, Inc. |
Tara N. Sainath; Google, Inc. |
Gabor Simko; Google, Inc. |
|
SLP-L1.3: COMPONENT FUSION: LEARNING REPLACEABLE LANGUAGE MODEL COMPONENT FOR END-TO-END SPEECH RECOGNITION SYSTEM |
Changhao Shan; Northwestern Polytechnical University |
Chao Weng; Tencent |
Guangsen Wang; Tencent |
Dan Su; Tencent |
Min Luo; Tencent |
Dong Yu; Tencent |
Lei Xie; Northwestern Polytechnical University |
|
SLP-L1.4: PARAMETER UNCERTAINTY FOR END-TO-END SPEECH RECOGNITION |
Stefan Braun; Institute of Neuroinformatics, University of Zurich and ETH Zurich |
Shih-Chii Liu; Institute of Neuroinformatics, University of Zurich and ETH Zurich |
|
SLP-L1.5: ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION |
Shane Settle; TTI-Chicago |
Kartik Audhkhasi; IBM |
Karen Livescu; TTI-Chicago |
Michael Picheny; IBM |
|
SLP-L1.6: PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR |
Murali Karthick Baskar; Brno University of Technology |
Lukáš Burget; Brno University of Technology |
Shinji Watanabe; Johns Hopkins University |
Martin Karafiat; Brno University of Technology |
Takaaki Hori; MERL |
Jan "Honza" Černocký; Brno University of Technology |
|