SLP-L25: Audio-visual speech/intent recognition
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)
Location: Room 102
Session Type: Lecture
Session Co-Chairs: Albert Zeyer, AppTek GmbH and Dmitriy Serdyuk, Google
Track: Speech and Language Processing
Click the to view the manuscript on IEEE Xplore Open Preview
Fri, 19 Apr, 08:20 - 08:40 (UTC +9)
 

SLP-L25.1: Conformer is all you need for visual speech recognition
Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Shah, Olivier Siohan, Google, United States of America
Fri, 19 Apr, 08:40 - 09:00 (UTC +9)
 

SLP-L25.2: LITEVSR: EFFICIENT VISUAL SPEECH RECOGNITION BY LEARNING FROM SPEECH REPRESENTATIONS OF UNLABELED DATA
Hendrik Laux, Emil Mededovic, University Hospital RWTH Aachen, Germany; Ahmed Hallawa, Lukas Martin, Arne Peine, Clinomic Medical GmbH, Germany; Anke Schmeink, RWTH Aachen University, Germany
Fri, 19 Apr, 09:00 - 09:20 (UTC +9)
 

SLP-L25.3: MULTILINGUAL AUDIO-VISUAL SPEECH RECOGNITION WITH HYBRID CTC/RNN-T FAST CONFORMER
Maxime Burchi, University of Würzburg, Germany; Krishna C. Puvvada, Jagadeesh Balam, Boris Ginsburg, NVIDIA, United States of America; Radu Timofte, University of Würzburg, Germany
Fri, 19 Apr, 09:20 - 09:40 (UTC +9)
 

SLP-L25.4: LCB-NET: LONG-CONTEXT BIASING FOR AUDIO-VISUAL SPEECH RECOGNITION
Fan Yu, Speech Lab of DAMO Academy, Alibaba Group, China; Haoxu Wang, Wuhan University, China; Xian Shi, Shiliang Zhang, Speech Lab of DAMO Academy, Alibaba Group, China
Fri, 19 Apr, 09:40 - 10:00 (UTC +9)
 

SLP-L25.5: VILAS: EXPLORING THE EFFECTS OF VISION AND LANGUAGE CONTEXT IN AUTOMATIC SPEECH RECOGNITION
Ziyi Ni, Minglun Han, Feilong Chen, Linghui Meng, Jing Shi, Pin Lv, Bo Xu, Institute of Automation, Chinese Academy of Sciences, China
Fri, 19 Apr, 10:00 - 10:20 (UTC +9)
 

SLP-L25.6: SDIF-DA: A SHALLOW-TO-DEEP INTERACTION FRAMEWORK WITH DATA AUGMENTATION FOR MULTI-MODAL INTENT DETECTION
Shijue Huang, Harbin Institute of Technology (Shenzhen), China; Libo Qin, Central South University, China; Bingbing Wang, Geng Tu, Ruifeng Xu, Harbin Institute of Technology (Shenzhen), China