Tricycle: Audio representation learning from sensor network data using self-supervision

Keyphrases

• Tricycle 100%
• Self-supervision 100%
• Audio Representation Learning 100%
• Limited Labeled Data 66%
• Audio Representation 66%
• Self-supervised Models 33%
• Self-supervised Representation Learning 33%
• Word Sequence 33%
• Single-modal 33%
• Timestamp Data 33%
• Pretext Task 33%
• Modal Data 33%

Psychology

• Neural Network 100%

Computer Science

• Limited Labeled Data 50%
• Self-Supervised Representation Learning 25%