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 |
|