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-3.6

CONTRASTIVE PREDICTION STRATEGIES FOR UNSUPERVISED SEGMENTATION AND CATEGORIZATION OF PHONEMES AND WORDS

Santiago Cuervo, Maciej Grabias, Grzegorz Ciesielski, Paweł Rychlikowski, University of Wroclaw, Poland; Jan Chorowski, University of Wroclaw / NavAlgo, Poland; Adrian Łańcucki, NVIDIA, Poland; Ricard Marxer, Université de Toulon, Aix Marseille Univ, CNRS, LIS, France

Session:
Self-supervised Learning for Speech and Audio Processing I

Track:
Machine Learning for Signal Processing

Location:
Gather Area H

Presentation Time:
Sun, 8 May, 20:00 - 20:45 China Time (UTC +8)
Sun, 8 May, 12:00 - 12:45 UTC

Session Chair:
Zheng-Hua Tan, Aalborg University
Presentation
Discussion
Resources
Session MLSP-3
MLSP-3.1: Characterizing the adversarial vulnerability of speech self-supervised learning
Haibin Wu, Hung-yi Lee, National Taiwan University, China; Bo Zheng, Xu Li, Xixin Wu, Helen Meng, The Chinese University of Hong Kong, Hong Kong
MLSP-3.2: UNIVERSAL PARALINGUISTIC SPEECH REPRESENTATIONS USING SELF-SUPERVISED CONFORMERS
Joel Shor, Verily Life Sciences, United States of America; Aren Jansen, Wei Han, Daniel Park, Yu Zhang, Google, United States of America
MLSP-3.3: A NOISE-ROBUST SELF-SUPERVISED PRE-TRAINING MODEL BASED SPEECH REPRESENTATION LEARNING FOR AUTOMATIC SPEECH RECOGNITION
Qiu-Shi Zhu, Jie Zhang, Zi-Qiang Zhang, Ming-Hui Wu, Xin Fang, Li-Rong Dai, University of Science and Technology of China, China
MLSP-3.4: AN ADAPTER BASED PRE-TRAINING FOR EFFICIENT AND SCALABLE SELF-SUPERVISED SPEECH REPRESENTATION LEARNING
Samuel Kessler, University of Oxford, United Kingdom of Great Britain and Northern Ireland; Bethan Thomas, Salah Karout, Huawei R&D UK, United Kingdom of Great Britain and Northern Ireland
MLSP-3.5: DRVC: A Framework of Any-to-Any Voice Conversion with Self-Supervised Learning
Qiqi Wang, The University of Auckland, New Zealand; Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao, Ping An Technology (Shenzhen) Co., Ltd., China
MLSP-3.6: CONTRASTIVE PREDICTION STRATEGIES FOR UNSUPERVISED SEGMENTATION AND CATEGORIZATION OF PHONEMES AND WORDS
Santiago Cuervo, Maciej Grabias, Grzegorz Ciesielski, Paweł Rychlikowski, University of Wroclaw, Poland; Jan Chorowski, University of Wroclaw / NavAlgo, Poland; Adrian Łańcucki, NVIDIA, Poland; Ricard Marxer, Université de Toulon, Aix Marseille Univ, CNRS, LIS, France