SPE-4.3
NEURAL-FST CLASS LANGUAGE MODEL FOR END-TO-END SPEECH RECOGNITION
Antoine Bruguier, Duc Le, Dangna Li, Zhe Liu, Bo Wang, Eun Chang, Fuchun Peng, Ozlem Kalinli, Mike Seltzer, Facebook, United States of America; Rohit Prabhavalkar, Google, United States of America
Session:
Language Modeling
Track:
Speech and Language Processing
Location:
Gather Area E
Presentation Time:
Sun, 8 May, 20:00 - 20:45 China Time (UTC +8)
Sun, 8 May, 12:00 - 12:45 UTC
Sun, 8 May, 12:00 - 12:45 UTC
Session Chair:
Ian Lane, CMU
Session SPE-4
SPE-4.1: CAPITALIZATION NORMALIZATION FOR LANGUAGE MODELING WITH AN ACCURATE AND EFFICIENT HIERARCHICAL RNN MODEL
Hao Zhang, You-Chi Cheng, Shankar Kumar, W. Ronny Huang, Mingqing Chen, Rajiv Mathews, Google, United States of America
SPE-4.2: ENHANCE RNNLMS WITH HIERARCHICAL MULTI-TASK LEARNING FOR ASR
Minguang Song, Yunxin Zhao, University of Missouri-Columbia, United States of America
SPE-4.3: NEURAL-FST CLASS LANGUAGE MODEL FOR END-TO-END SPEECH RECOGNITION
Antoine Bruguier, Duc Le, Dangna Li, Zhe Liu, Bo Wang, Eun Chang, Fuchun Peng, Ozlem Kalinli, Mike Seltzer, Facebook, United States of America; Rohit Prabhavalkar, Google, United States of America
SPE-4.4: LATTICEBART: LATTICE-TO-LATTICE PRE-TRAINING FOR SPEECH RECOGNITION
Lingfeng Dai, Lu Chen, Zhikai Zhou, Kai Yu, Shanghai Jiao Tong University, China
SPE-4.5: RESCOREBERT: DISCRIMINATIVE SPEECH RECOGNITION RESCORING WITH BERT
Liyan Xu, Yile Gu, Jari Kolehmainen, Haidar Khan, Ankur Gandhe, Ariya Rastrow, Andreas Stolcke, Ivan Bulyko, Amazon Alexa AI, United States of America
SPE-4.6: Hybrid sub-word segmentation for handling long tail in morphologically rich low resource languages
Sreeja Manghat, Sreeram Manghat, IEEE Graduate Member, India; Tanja Schultz, Cognitive Systems Lab, University Bremen, Germany, Germany