SPE-54.5
Temporal Early Exiting for Streaming Speech Commands Recognition
Raphael Tang, Karun Kumar, Piyush Vyas, Gefei Yang, Yajie Mao, Craig Murray, Comcast, United States of America; Ji Xin, Jimmy Lin, University of Waterloo, Canada; Wenyan Li, SenseTime, China
Session:
Keyword Spotting
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Wed, 11 May, 21:00 - 21:45 China Time (UTC +8)
Wed, 11 May, 13:00 - 13:45 UTC
Wed, 11 May, 13:00 - 13:45 UTC
Session Chair:
Zhijian Ou, Tsinghua University
Session SPE-54
SPE-54.1: JOINT EGO-NOISE SUPPRESSION AND KEYWORD SPOTTING ON SWEEPING ROBOTS
Yueyue Na, Ziteng Wang, Qiang Fu, Alibaba Group, China; Liang Wang, Sun Yat-sen University (SYSU), China
SPE-54.2: PROGRESSIVE CONTINUAL LEARNING FOR SPOKEN KEYWORD SPOTTING
Yizheng Huang, Nancy Chen, Institute for Infocomm Research, A*STAR, Singapore, Singapore; Nana Hou, Nanyang Technological University, Singapore, Singapore
SPE-54.3: UNIFIED SPECULATION, DETECTION, AND VERIFICATION KEYWORD SPOTTING
Geng-shen Fu, Thibaud Senechal, Aaron Challenner, Tao Zhang, Amazon, United States of America
SPE-54.4: LEARNING DECOUPLING FEATURES THROUGH ORTHOGONALITY REGULARIZATION
Li Wang, Rongzhi Gu, Yuexian Zou, Peking University, China; Weiji Zhuang, Peng Gao, Yujun Wang, Xiaomi Inc., China
SPE-54.5: Temporal Early Exiting for Streaming Speech Commands Recognition
Raphael Tang, Karun Kumar, Piyush Vyas, Gefei Yang, Yajie Mao, Craig Murray, Comcast, United States of America; Ji Xin, Jimmy Lin, University of Waterloo, Canada; Wenyan Li, SenseTime, China
SPE-54.6: A STUDY OF DESIGNING COMPACT AUDIO-VISUAL WAKE WORD SPOTTING SYSTEM BASED ON ITERATIVE FINE-TUNING IN NEURAL NETWORK PRUNING
Hengshun Zhou, Jun Du, University of Science and Technology of China, China; Chao-Han Huck Yang, Chin-Hui Lee, Georgia Institute of Technology, United States of America; Shifu Xiong, iFlytek Research, China