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-L4: Machine Learning for Audio and Speech
Thu, 26 May, 13:00 - 15:00 China Time (UTC +8)
Thu, 26 May, 05:00 - 07:00 UTC
Location: Roselle Junior Ballroom 4611-3
Session Co-Chairs: George Sammit, Southwest Research Institute and Toshihisa Tanaka, Tokyo University of Agriculture and Technology
Track: Machine Learning for Signal Processing

MLSP-L4.1: ENABLING ON-DEVICE TRAINING OF SPEECH RECOGNITION MODELS WITH FEDERATED DROPOUT
Dhruv Guliani, Lillian Zhou, Changwan Ryu, Tien-Ju Yang, Harry Zhang, Yonghui Xiao, Francoise Beaufays, Giovanni Motta, Google Inc, United States of America

MLSP-L4.2: Self supervised representation learning with deep clustering for acoustic unit discovery from raw speech
Varun Krishna, Sriram Ganapathy, LEAP lab, Indian Institute of Science, Bangalore, India., India

MLSP-L4.3: RANK-BASED LOSS FOR LEARNING HIERARCHICAL REPRESENTATIONS
Ines Nolasco, Queen Mary university of London, United Kingdom of Great Britain and Northern Ireland; Dan Stowell, Tilburg University, Netherlands

MLSP-L4.4: AUTOMATED PROSODY CLASSIFICATION FOR ORAL READING FLUENCY WITH QUADRATIC KAPPA LOSS AND ATTENTIVE X-VECTORS
George Sammit, Zhongjie Wu, Yihao Wang, Zhongdi Wu, Akihito Kamata, Eric C. Larson, Southern Methodist University, United States of America; Joseph Nese, University of Oregon, United States of America

MLSP-L4.5: DEEP AUGMENTED MUSIC ALGORITHM FOR DATA-DRIVEN DOA ESTIMATION
Julian P. Merkofer, Guy Revach, ETH Zurich, Switzerland; Nir Shlezinger, Ben-Gurion University of the Negev, Israel; Ruud J. G. van Sloun, Eindhoven University of Technology, Netherlands

MLSP-L4.6: SELF-SUPERVISED LEARNING METHOD USING MULTIPLE SAMPLING STRATEGIES FOR GENERAL-PURPOSE AUDIO REPRESENTATION
Ibuki Kuroyanagi, Nagoya University, Japan; Tatsuya Komatsu, LINE Corporation, Japan

MLSP-L4.7: EXPLORING HETEROGENEOUS CHARACTERISTICS OF LAYERS IN ASR MODELS FOR MORE EFFICIENT TRAINING
Lillian Zhou, Dhruv Guliani, Andreas Kabel, Giovanni Motta, Françoise Beaufays, Google LLC, United States of America

MLSP-L4.8: QUANTUM FEDERATED LEARNING WITH QUANTUM DATA
Mahdi Chehimi, Walid Saad, Virginia Tech, United States of America