IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
MLSP-L3: Learning Theory and Methods
Wed, 25 May, 13:00 - 15:30 China Time (UTC +8)
Wed, 25 May, 05:00 - 07:30 UTC
Location: Roselle Junior Ballroom 4611-3
Session Co-Chairs: Reinmar Kobler, RIKEN and Andreas Maier, Friedrich-Alexander-Universität Erlangen-Nürnberg
Track: Machine Learning for Signal Processing

MLSP-L3.1: UNCERTAINTY IN DATA-DRIVEN KALMAN FILTERING FOR PARTIALLY KNOWN STATE-SPACE MODELS
Itzik Klein, University of Haifa, Israel; Guy Revach, Jonas E. Mehr, ETH Zürich, Switzerland; Nir Shlezinger, Ben-Gurion University of the Negev, Israel; Ruud J. G. van Sloun, Eindhoven University of Technology, and with Phillips Research, Netherlands; Yonina. C. Eldar, Weizmann Institute of Science, Israel

MLSP-L3.2: CONTROLLING THE FRÉCHET VARIANCE IMPROVES BATCH NORMALIZATION ON THE SYMMETRIC POSITIVE DEFINITE MANIFOLD
Reinmar Kobler, Jun-ichiro Hirayama, Motoaki Kawanabe, RIKEN, Japan

MLSP-L3.3: VARIATIONAL BAYESIAN TENSOR NETWORKS WITH STRUCTURED POSTERIORS
Kriton Konstantinidis, Yao Xu, Danilo Mandic, IMPERIAL COLLEGE LONDON, United Kingdom of Great Britain and Northern Ireland; Qibin Zhao, RIKEN CENTER FOR ADVANCED INTELLIGENCE PROJECT, Japan

MLSP-L3.4: A MULTI-RESOLUTION LOW-RANK TENSOR DECOMPOSITION
Sergio Rozada Doval, Antonio G. Marques, King Juan Carlos University, Spain

MLSP-L3.5: LOW-COMPLEXITY ATTENTION MODELLING VIA GRAPH TENSOR NETWORKS
Yao Lei Xu, Kriton Konstantinidis, Shengxi Li, Danilo P. Mandic, Imperial College London, United Kingdom of Great Britain and Northern Ireland; Ljubiša Stanković, University of Montenegro, Montenegro

MLSP-L3.6: KRYLOV-LEVENBERG-MARQUARDT ALGORITHM FOR STRUCTURED TUCKER TENSOR DECOMPOSITIONS
Petr Tichavsky, Institute of Information Theory and Automation of the CAS, Czechia; Anh-Huy Phan, Andrzej Cichocki, Skolkovo Institute of Science and Technology, Russian Federation

MLSP-L3.7: MIXTURE MODEL AUTO-ENCODERS: DEEP CLUSTERING THROUGH DICTIONARY LEARNING
Alexander Lin, Demba Ba, Harvard University, United States of America; Andrew Song, Massachusetts Institute of Technology, United States of America

MLSP-L3.8: CONTRASTIVE PREDICTIVE CODING FOR ANOMALY DETECTION OF FETAL HEALTH FROM THE CARDIOTOCOGRAM
Ivar R. de Vries, Iris A.M. Huijben, Ruud J.G. van Sloun, Rik Vullings, Eindhoven University of Technology, Netherlands; René D. Kok, Nemo Healthcare BV, Netherlands

MLSP-L3.9: ORCA-PARTY: AN AUTOMATIC KILLER WHALE SOUND TYPE SEPARATION TOOLKIT USING DEEP LEARNING
Christian Bergler, Manuel Schmitt, Andreas Maier, Elmar Nöth, Friedrich-Alexander-University Erlangen-Nuremberg, Germany; Rachael Xi Cheng, Leibniz Institute for Zoo and Wildlife Research, Germany; Volker Barth, Anthro-Media, Germany

MLSP-L3.10: FEATURE AUGMENTATION LEARNING FOR FEW-SHOT PALMPRINT IMAGE RECOGNITION WITH UNCONSTRAINED ACQUISITION
Kunlei Jing, Xinman Zhang, Xi’an Jiaotong University, China; Zhiyuan Yang, Bihan Wen, Nanyang Technological University, China