SPE-73.4
ADAPTIVE DISCOUNTING OF IMPLICIT LANGUAGE MODELS IN RNN-TRANSDUCERS
Vinit Unni, Preethi Jyothi, Sunita Sarawagi, Indian Institute of Technology Bombay, India; Shreya Khare, Ashish Mittal, Samarth Bharadwaj, IBM Research, India
Session:
Speech Recognition: Neural Transducer Models
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Thu, 12 May, 22:00 - 22:45 China Time (UTC +8)
Thu, 12 May, 14:00 - 14:45 UTC
Thu, 12 May, 14:00 - 14:45 UTC
Session Chair:
Tara Sainath, Google
Session SPE-73
SPE-73.1: Transducer-Based Streaming Deliberation For Cascaded Encoders
Ke Hu, Tara Sainath, Arun Narayanan, Ruoming Pang, Trevor Strohman, Google, United States of America
SPE-73.2: IMPROVING THE LATENCY AND QUALITY OF CASCADED ENCODERS
Tara Sainath, Yanzhang He, Arun Narayanan, Rami Botros, Weiran Wang, David Qiu, Chung-cheng Chiu, Rohit Prabhavalkar, Alexander Gruenstein, Anmol Gulati, Bo Li, David Rybach, Emmanuel Guzman, Ian McGraw, James Qin, Krzysztof Choromanski, Qiao Liang, Robert David, Ruoming Pang, Shuoyiin Chang, Trevor Strohman, W. Ronny Huang, Wei Han, Yonghui Wu, Yu Zhang, Google, Inc., United States of America
SPE-73.3: IMPROVING THE FUSION OF ACOUSTIC AND TEXT REPRESENTATIONS IN RNN-T
Chao Zhang, Bo Li, Zhiyun Lu, Tara Sainath, Shuo-Yiin Chang, Google LLC, United Kingdom of Great Britain and Northern Ireland
SPE-73.4: ADAPTIVE DISCOUNTING OF IMPLICIT LANGUAGE MODELS IN RNN-TRANSDUCERS
Vinit Unni, Preethi Jyothi, Sunita Sarawagi, Indian Institute of Technology Bombay, India; Shreya Khare, Ashish Mittal, Samarth Bharadwaj, IBM Research, India
SPE-73.5: INTEGRATING TEXT INPUTS FOR TRAINING AND ADAPTING RNN TRANSDUCER ASR MODELS
Samuel Thomas, Brian Kingsbury, George Saon, Hong-Kwang Kuo, IBM Research AI, United States of America
SPE-73.6: Factorized Neural Transducer for Efficient Language Model Adaptation
Xie Chen, Zhong Meng, Sarangarajan Parthasarathy, Jinyu Li, Microsoft Corporation, United States of America