SPE-14.1
MASSIVELY MULTILINGUAL ASR: A LIFELONG LEARNING SOLUTION
Bo Li, Ruoming Pang, Yu Zhang, Tara Sainath, Trevor Strohman, Parisa Haghani, Yun Zhu, Brian Farris, Neeraj Gaur, Manasa Prasad, Google, United States of America
Session:
Multi-lingual ASR
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Sun, 8 May, 23:00 - 23:45 China Time (UTC +8)
Sun, 8 May, 15:00 - 15:45 UTC
Sun, 8 May, 15:00 - 15:45 UTC
Session Chair:
George Saon, IBM
Session SPE-14
SPE-14.1: MASSIVELY MULTILINGUAL ASR: A LIFELONG LEARNING SOLUTION
Bo Li, Ruoming Pang, Yu Zhang, Tara Sainath, Trevor Strohman, Parisa Haghani, Yun Zhu, Brian Farris, Neeraj Gaur, Manasa Prasad, Google, United States of America
SPE-14.2: JOINT UNSUPERVISED AND SUPERVISED TRAINING FOR MULTILINGUAL ASR
Junwen Bai, Cornell University, United States of America; Bo Li, Yu Zhang, Ankur Bapna, Nikhil Siddhartha, Khe Chai Sim, Tara Sainath, Google, United States of America
SPE-14.3: MULTILINGUAL SECOND-PASS RESCORING FOR AUTOMATIC SPEECH RECOGNITION SYSTEMS
Neeraj Gaur, Tongzhou Chen, Ehsan Variani, Parisa Haghani, Bhuvana Ramabhadran, Pedro Moreno, Google, United States of America
SPE-14.4: JOINT MODELING OF CODE-SWITCHED AND MONOLINGUAL ASR VIA CONDITIONAL FACTORIZATION
Brian Yan, Siddharth Dalmia, Dan Berrebbi, Shinji Watanabe, Carnegie Mellon University, United States of America; Chunlei Zhang, Meng Yu, Shi-Xiong Zhang, Chao Weng, Dong Yu, Tencent AI Lab, United States of America
SPE-14.5: BILINGUAL END-TO-END ASR WITH BYTE-LEVEL SUBWORDS
Liuhui Deng, Roger Hsiao, Arnab Ghoshal, Apple, United States of America
SPE-14.6: A Configurable Multilingual Model is All You Need to Recognize All Languages
Long Zhou, Shujie Liu, Microsoft Research Asia, China; Jinyu Li, Eric Sun, Microsoft Speech and Language Group, United States of America