Jointly Learning Visual and Auditory Speech Representations from Raw Data.
Alexandros HaliassosPingchuan MaRodrigo MiraStavros PetridisMaja PanticPublished in: ICLR (2023)
Keyphrases
- raw data
- learning algorithm
- object recognition
- data sets
- visual learning
- visual information
- databases
- language acquisition
- learning tasks
- online learning
- image quality
- active learning
- learning process
- reinforcement learning
- low level
- supervised learning
- prior knowledge
- relational databases
- visual representation
- high level
- visual processing
- machine learning