MLSP-L23: Self-Supervised Representation Learning
Oral
Thu, 7 May, 14:00 - 16:00
Location: Room 113
Session Type: Oral
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview
Thu, 7 May, 14:00 - 14:20

MLSP-L23.1: PC-SSL: A PREDICTIVE CODING-BASED SELF-SUPERVISED LEARNING FRAMEWORK FOR EEG EMOTION RECOGNITION
Niki Sheibani, Naimul Khan, Toronto Metropolitan University, Canada
Thu, 7 May, 14:20 - 14:40

MLSP-L23.2: OPTIMIZING DOMAIN-ADAPTIVE SELF-SUPERVISED LEARNING FOR CLINICAL VOICE-BASED DISEASE CLASSIFICATION
Weixin Liu, Bowen Qu, Vanderbilt University, United States of America; Matthew Pontell, Maria Powell, Bradley Malin, Zhijun Yin, Vanderbilt University Medical Center, United States of America
Thu, 7 May, 14:40 - 15:00

MLSP-L23.3: H2DFD: SELF-SUPERVISED FAKE NEWS DETECTION VIA A NOVEL HYPERBOLIC HYPERGRAPH DIFFUSION MODEL
Mengyao Peng, Yiping Ma, Hongyan Gu, Xinyi Zhang, Yedi Ma, Xinli Huang, East China Normal University, China
Thu, 7 May, 15:00 - 15:20

MLSP-L23.4: INPUT-ADAPTIVE DIFFERENTIABLE FILTERBANKS VIA HYPERNETWORKS FOR ROBUST SPEECH PROCESSING
Zikun Quan, University College London, United Kingdom of Great Britain and Northern Ireland; Weilin Zhou, Nanjing Tech University, China; Gaoyuan du, Amazon, United States of America
Thu, 7 May, 15:20 - 15:40

MLSP-L23.5: MT-HUBERT: SELF-SUPERVISED MIX-TRAINING FOR FEW-SHOT KEYWORD SPOTTING IN MIXED SPEECH
Junming Yuan, Xinjiang University, China; Ying Shi, Harbin Institute of Technology, China; Dong Wang, Tsinghua University, China; Lantian Li, Beijing University of Posts and Telecommunications, China; Askar Hamdulla, Xinjiang University, China
Thu, 7 May, 15:40 - 16:00

MLSP-L23.6: A STUDY OF DATA SELECTION STRATEGIES FOR PRE-TRAINING SELF-SUPERVISED SPEECH MODELS
Ryan Whetten, Avignon Université, France; Titouan Parcollet, University of Cambridge, United Kingdom of Great Britain and Northern Ireland; Marco Dinarelli, Université Grenoble Alpes, France; Yannick Estève, Avignon Université, France