MMSP-L2.2
HOURGLASS-AVSR: DOWN-UP SAMPLING-BASED COMPUTATIONAL EFFICIENCY MODEL FOR AUDIO-VISUAL SPEECH RECOGNITION
Fan Yu, Haoxu Wang, Ziyang Ma, Shiliang Zhang, Speech Lab of DAMO Academy, Alibaba Group, China
Session:
MMSP-L2: Audio-Visual Speech Processing Lecture
Track:
Multimedia Signal Processing
Location:
Room E1
Presentation Time:
Wed, 17 Apr, 08:40 - 09:00 (UTC +9)
Session Co-Chairs:
Li Liu, HKUST Guangzhou, China and Prasanta Ghosh, Indian Institute of Science (IISc), Bangalore
Session MMSP-L2
MMSP-L2.1: THE MULTIMODAL INFORMATION BASED SPEECH PROCESSING (MISP) 2023 CHALLENGE: AUDIO-VISUAL TARGET SPEAKER EXTRACTION
Shilong Wu, Chenxi Wang, Hang Chen, Yusheng Dai, Chenyue Zhang, Ruoyu Wang, Hongbo Lan, Jun Du, University of Science and Technology of China, China; Chin-hui Lee, Georgia Institute of Technology, United States of America; Jingdong Chen, Northwestern Polytechnical University, China; Sabato Marco Siniscalchi, Kore University of Enna, Italy; Odette Scharenborg, Delft University of Technology, Netherlands; Zhong-Qiu Wang, Carnegie Mellon University, United States of America; Jia Pan, Jianqing Gao, iFlytek Research, China
MMSP-L2.2: HOURGLASS-AVSR: DOWN-UP SAMPLING-BASED COMPUTATIONAL EFFICIENCY MODEL FOR AUDIO-VISUAL SPEECH RECOGNITION
Fan Yu, Haoxu Wang, Ziyang Ma, Shiliang Zhang, Speech Lab of DAMO Academy, Alibaba Group, China
MMSP-L2.3: TALKNCE: IMPROVING ACTIVE SPEAKER DETECTION WITH TALK-AWARE CONTRASTIVE LEARNING
Chaeyoung Jung, Suyeon Lee, Kihyun Nam, Kyeongha Rho, Korea Advanced Institute of Science and Technology, Korea, Republic of; You Jin Kim, Naver Cloud Corporation, Korea, Republic of; Youngjoon Jang, Joon Son Chung, Korea Advanced Institute of Science and Technology, Korea, Republic of
MMSP-L2.4: MLCA-AVSR: MULTI-LAYER CROSS ATTENTION FUSION BASED AUDIO-VISUAL SPEECH RECOGNITION
He Wang, Pengcheng Guo, Northwestern Polytechnical University, China; Pan Zhou, Li Auto, China; Lei Xie, Northwestern Polytechnical University, China
MMSP-L2.5: AUDIO-VISUAL SPEECH RECOGNITION IN-THE-WILD: MULTI-ANGLE VEHICLE CABIN CORPUS AND ATTENTION-BASED METHOD
Alexandr Axyonov, Dmitry Ryumin, Denis Ivanko, St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation; Alexey Kashevnik, ITMO University, Russian Federation; Alexey Karpov, St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation
MMSP-L2.6: GLMB 3D SPEAKER TRACKING WITH VIDEO-ASSISTED MULTI-CHANNEL AUDIO OPTIMIZATION FUNCTIONS
Xinyuan Qian, University of Science and Technology Beijing, China; Zexu Pan, National University of Singapore, Singapore; Qiquan Zhang, University of New South Wales, Australia; Kainan Chen, Eigenspace, China; Shoufeng Lin, Curtin Unviersity, Australia
Contacts