SLP-P20.10
AN INVESTIGATION OF DISTRIBUTION ALIGNMENT IN MULTI-GENRE SPEAKER RECOGNITION
Zhenyu Zhou, Junhui Chen, Beijing University of Posts and Telecommunications, China; Namin Wang, Huawei Cloud, China; Lantian Li, Beijing University of Posts and Telecommunications, China; Dong Wang, Tsinghua University, China
Session:
SLP-P20: Speaker Recognition and Anonymization Poster
Track:
Speech and Language Processing
Location:
Poster Zone 4A
Poster Board PZ-4A.10
Poster Board PZ-4A.10
Presentation Time:
Thu, 18 Apr, 08:20 - 10:20 (UTC +9)
Session Co-Chairs:
Ville Hautamäki, University of Eastern Finland and Xiaoxiao Miao, Singapore Institute of Technology
Session SLP-P20
SLP-P20.1: MULTI-VIEW SPEAKER EMBEDDING LEARNING FOR ENHANCED STABILITY AND DISCRIMINABILITY
Liang He, Tsinghua University, China; Zhihua Fang, Xinjiang University, China; Zuoer Chen, Tsinghua University, China; Minqiang Xu, iFly Digital Technology, China; Ying Meng, Xinjiang University, China; Penghao Wang, Tsinghua University, China
SLP-P20.2: WHAT DO SELF-SUPERVISED SPEECH AND SPEAKER MODELS LEARN? NEW FINDINGS FROM A CROSS MODEL LAYER-WISE ANALYSIS
Takanori Ashihara, Marc Delcroix, Takafumi Moriya, Kohei Matsuura, Taichi Asami, Yusuke Ijima, NTT Corporation, Japan
SLP-P20.3: A SPEAKER RECOGNITION METHOD BASED ON STABLE LEARNING
Jian Zhang, Jing Ma, Xiaochen Guo, Xinjiang University, China; Lin Li, Xiamen University, China; Liang He, Tsinghua University and Xinjiang University, China
SLP-P20.4: Generating High-quality Adversarial Examples with Universal Perturbation-Based Adaptive Network and Improved Perceptual Loss
Zhuhai Li, Wu Guo, Jie Zhang, University of Science and Technology of China, China
SLP-P20.5: A STUDY ON GRAPH EMBEDDING FOR SPEAKER RECOGNITION
Liang He, Tsinghua University, China; Ruida Li, Xinjiang University, China
SLP-P20.6: POST-TRAINING EMBEDDING ALIGNMENT FOR DECOUPLING ENROLLMENT AND RUNTIME SPEAKER RECOGNITION MODELS
Chenyang Gao, Rutgers, The State University of New Jersey, United States of America; Brecht Desplanques, Chelsea J.-T. Ju, Aman Chadha, Amazon Alexa AI, United States of America; Andreas Stolcke, Uniphore, United States of America
SLP-P20.7: CONTRASTIVE SPEAKER EMBEDDING WITH SEQUENTIAL DISENTANGLEMENT
Youzhi Tu, Man-Wai Mak, The Hong Kong Polytechnic University, Hong Kong; Jen-Tzung Chien, National Yang Ming Chiao Tung University, Taiwan
SLP-P20.8: Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition
Shuai Wang, Shenzhen Research Institute of Big Data, China; Qibing Bai, Chinese University of Hong Kong, Shenzhen (CUHK-SZ), China; Qi Liu, Jianwei Yu, Tencent, China; Zhengyang Chen, Bing Han, Yanmin Qian, Shanghai Jiao Tong University, China; Haizhou Li, Chinese University of Hong Kong, Shenzhen (CUHK-SZ), China
SLP-P20.9: SYNVOX2: TOWARDS A PRIVACY-FRIENDLY VOXCELEB2 DATASET
Xiaoxiao Miao, Singapore Institute of Technology, Japan; Xin Wang, Erica Cooper, Junichi Yamagishi, National Institute of Infomatics, Japan; Nicholas Evans, Massimiliano Todisco, EURECOM, France; Jean-François Bonastre, Mickael Rouvier, University of Avignon, France
SLP-P20.10: AN INVESTIGATION OF DISTRIBUTION ALIGNMENT IN MULTI-GENRE SPEAKER RECOGNITION
Zhenyu Zhou, Junhui Chen, Beijing University of Posts and Telecommunications, China; Namin Wang, Huawei Cloud, China; Lantian Li, Beijing University of Posts and Telecommunications, China; Dong Wang, Tsinghua University, China
SLP-P20.11: DISCRETE AUDIO REPRESENTATION AS AN ALTERNATIVE TO MEL-SPECTROGRAMS FOR SPEAKER AND SPEECH RECOGNITION
Krishna Puvvada, Nithin koluguri, Kunal Dhawan, Jagadeesh Balam, Boris Ginsburg, NVIDIA, United States of America
SLP-P20.12: Modeling pseudo-speaker uncertainty in voice anonymization
Liping Chen, University of Science and Technology of China, China; KongAik Lee, Singapore Institute of Technology, Singapore; Wu Guo, Zhen-Hua Ling, University of Science and Technology of China, China
SLP-P20.13: SPEAKER ANONYMIZATION USING ORTHOGONAL HOUSEHOLDER NEURAL NETWORK
Xiaoxiao Miao, Singapore Institute of Technology, Singapore; Xin Wang, Erica Cooper, Junichi Yamagishi, National Institute of Informatics, Japan
Contacts