MLSP-P5.7
Balanced Learning for Multi-Domain Long-tailed Speaker Recognition
Janghoon Cho, Sunghyun Park, Hyunsin Park, Hyoungwoo Park, Seunghan Yang, Sungrack Yun, Qualcomm, Korea, Republic of
Session:
MLSP-P5: Deep Learning Techniques II Poster
Track:
Machine Learning for Signal Processing
Location:
Poster Zone 2A
Poster Board PZ-2A.7
Poster Board PZ-2A.7
Presentation Time:
Tue, 16 Apr, 16:30 - 18:30 (UTC +9)
Session Chair:
Xixin Wu, Chinese University of Hong Kong
Session MLSP-P5
MLSP-P5.1: MULTIWAY-ADAPTER: ADAPTING MULTIMODAL LARGE LANGUAGE MODELS FOR SCALABLE IMAGE-TEXT RETRIEVAL
Zijun Long, George Killick, Richard McCreadie, Gerardo Aragon Camarasa, The University of Glasgow, United Kingdom of Great Britain and Northern Ireland
MLSP-P5.2: Dataset Distillation with Channel Efficient Process
Wenbo Zhou, Guoqing Zheng, Xinghao Ding, School of Informatics, Xiamen University, China
MLSP-P5.3: DEFORMATION AND PENETRATION HYBRID DETECTION-NET FOR PARCELS INSPECTION IN INDUSTRIAL SUPPLY CHAIN
Zhi Chen, Jinan University, China; Cuifeng Du, Cetc Potevio Science Technology Co., Ltd, China; Xiujie Huang, Zelong Lin, Yuyu Zhou, Quanlong Guan, Zhefu Li, Shuanghuan Lv, Jinan University, China; Xiaofeng Wu, Guangzhou Polytechnic of Sports, China; Xiaotian Zhuang, Beijing JD Zhenshi Information Technology Co., Ltd, China
MLSP-P5.4: Augment on Manifold: Mixup Regularization with UMAP
Yousef El-Laham, Elizabeth Fons, J.P. Morgan AI Research, United States of America; Dillon Daudert, Stony Brook University, United States of America; Svitlana Vyetrenko, J.P. Morgan AI Research, United States of America
MLSP-P5.5: IMPROVING CONTINUAL LEARNING OF ACOUSTIC SCENE CLASSIFICATION VIA MUTUAL INFORMATION OPTIMIZATION
Muqiao Yang, Carnegie Mellon University, United States of America; Umberto Cappellazzo, University of Trento, Italy; Xiang Li, Bhiksha Raj, Carnegie Mellon University, United States of America
MLSP-P5.6: Non Commutative Convolutional Signal Models in Neural Networks: Stability to Small Deformations
Alejandro Parada-Mayorga, University of Pennsylvania, United States of America; Landon Butler, University of California Berkeley, United States of America; Alejandro Ribeiro, University of Pennsylvania, United States of America
MLSP-P5.7: Balanced Learning for Multi-Domain Long-tailed Speaker Recognition
Janghoon Cho, Sunghyun Park, Hyunsin Park, Hyoungwoo Park, Seunghan Yang, Sungrack Yun, Qualcomm, Korea, Republic of
MLSP-P5.8: UNROLLED PROXIMAL GRADIENT DESCENT METHOD FOR NON-NEGATIVE LEAST SQUARES PROBLEM
Akash Sen, Indian Institute of Technology, Hyderabad, India; Pradyumna Pradhan, Ramunaidu Randhi, Indian Institute of Petroleum and Energy (IIPE), Visakhapatnam, India; Subrahmanya Sastry Challa, Indian Institute of Technology, Hyderabad, India
MLSP-P5.9: IMAGE AUGMENTATION WITH CONTROLLED DIFFUSION FOR WEAKLY-SUPERVISED SEMANTIC SEGMENTATION
Wangyu Wu, Xi’an Jiaotong-Liverpool University; The University of Liverpool, China; Tianhong Dai, University of Aberdeen, United Kingdom of Great Britain and Northern Ireland; Xiaowei Huang, The University of Liverpool, United Kingdom of Great Britain and Northern Ireland; Fei Ma, Jimin Xiao, Xi’an Jiaotong-Liverpool University, China
MLSP-P5.10: Multi-Attention Enhanced Discriminator for GAN-Based Anomalous Sound Detection
Shuxin Liu, Jiliang Li, Wei Ke, Xi'an Jiaotong University, China; Hao Yin, Tsinghua University, China
MLSP-P5.11: REAL-TIME MULTI-HUMAN PARSING ON EMBEDDED DEVICES
Rockson Agyeman, Bernhard Rinner, University of Klagenfurt, Austria
MLSP-P5.12: A UNIFIED DNN-BASED SYSTEM FOR INDUSTRIAL PIPELINE SEGMENTATION
Dimitrios Psarras, Christos Papaioannidis, Vasileios Mygdalis, Ioannis Pitas, Aristotle University of Thessaloniki, Greece
Contacts