SPE-53.3
REAL ADDITIVE MARGIN SOFTMAX FOR SPEAKER VERIFICATION
Lantian Li, Ruiqian Nai, Dong Wang, Tsinghua University, China
Session:
Speaker Recognition VII: Neural Network Architecture
Track:
Speech and Language Processing
Location:
Gather Area B
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:
Hynek Boril, University of Wisconsin-Platteville
Session SPE-53
SPE-53.1: MFA: TDNN WITH MULTI-SCALE FREQUENCY-CHANNEL ATTENTION FOR TEXT-INDEPENDENT SPEAKER VERIFICATION WITH SHORT UTTERANCES
Tianchi Liu, Kong Aik Lee, Agency for Science, Technology and Research, Singapore; Rohan Kumar Das, Fortemedia Singapore, Singapore; Haizhou Li, National University of Singapore, Singapore
SPE-53.2: MLP-SVNET : A MULTI-LAYER PERCEPTRONS BASED NETWORK FOR SPEAKER VERIFICATION
Bing Han, Zhengyang Chen, Bei Liu, Yanmin Qian, Shanghai Jiao Tong University, China
SPE-53.3: REAL ADDITIVE MARGIN SOFTMAX FOR SPEAKER VERIFICATION
Lantian Li, Ruiqian Nai, Dong Wang, Tsinghua University, China
SPE-53.4: STATISTICAL PYRAMID DENSE TIME DELAY NEURAL NETWORK FOR SPEAKER VERIFICATION
Zi-Kai Wan, Qing-Hua Ren, You-Cai Qin, Qi-Rong Mao, Jiangsu University, China
SPE-53.5: ON THE IMPORTANCE OF DIFFERENT FREQUENCY BINS FOR SPEAKER VERIFICATION
Aiwen Deng, Wenxiong Kang, Feiqi Deng, South China University of Technology, China; Shuai Wang, Shanghai Jiao Tong University, China
SPE-53.6: SELF-KNOWLEDGE DISTILLATION VIA FEATURE ENHANCEMENT FOR SPEAKER VERIFICATION
Bei Liu, Haoyu Wang, Zhengyang Chen, Shuai Wang, Yanmin Qian, Shanghai Jiao Tong University, China