SPE-25.5
MULTI-QUERY MULTI-HEAD ATTENTION POOLING AND INTER-TOPK PENALTY FOR SPEAKER VERIFICATION
Miao Zhao, Yufeng Ma, Yu Zheng, Min Liu, Minqiang Xu, SpeakIn Technologies Co. Ltd., China; Yiwei Ding, Fudan University, China
Session:
Speaker Recognition IV: Attention Mechanism
Track:
Speech and Language Processing
Location:
Gather Area B
Presentation Time:
Mon, 9 May, 22:00 - 22:45 China Time (UTC +8)
Mon, 9 May, 14:00 - 14:45 UTC
Mon, 9 May, 14:00 - 14:45 UTC
Session Chair:
Alicia Lozano-Diez, Universidad Autonoma de Madrid
Session SPE-25
SPE-25.1: ATTENTION BACK-END FOR AUTOMATIC SPEAKER VERIFICATION WITH MULTIPLE ENROLLMENT UTTERANCES
Chang Zeng, Junichi Yamagishi, National Institute of Informatics, SOKENDAI, Japan; Xin Wang, Erica Cooper, Xiaoxiao Miao, National Institute of Informatics, Japan
SPE-25.2: Simple Attention Module based Speaker Verification with Iterative noisy label detection
Xiaoyi Qin, Wuhan University, China; Na Li, Chao Weng, Dan Su, Tencent AI Lab, China; Ming Li, Duke Kunshan University, China
SPE-25.3: LOCAL INFORMATION MODELING WITH SELF-ATTENTION FOR SPEAKER VERIFICATION
Bing Han, Zhengyang Chen, Yanmin Qian, Shanghai Jiao Tong University, China
SPE-25.4: MULTI-VIEW SELF-ATTENTION BASED TRANSFORMER FOR SPEAKER RECOGNITION
Rui Wang, Zhihua Wei, Tongji University, China; Junyi Ao, Tom Ko, Yu Zhang, Southern University of Science and Technology, China; Long Zhou, Shujie Liu, Microsoft Research Asia, China; Qing Li, The Hong Kong Polytechnic University, Hong Kong
SPE-25.5: MULTI-QUERY MULTI-HEAD ATTENTION POOLING AND INTER-TOPK PENALTY FOR SPEAKER VERIFICATION
Miao Zhao, Yufeng Ma, Yu Zheng, Min Liu, Minqiang Xu, SpeakIn Technologies Co. Ltd., China; Yiwei Ding, Fudan University, China
SPE-25.6: Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemic Analysis
Seong-Hu Kim, Hyeonuk Nam, Yong-Hwa Park, Korea Advanced Institute of Science and Technology, Korea, Republic of