Self-Supervised Audio-Visual Speaker Representation with Co-Meta Learning.
Hui ChenHanyi ZhangLongbiao WangKong Aik LeeMeng LiuJianwu DangPublished in: ICASSP (2023)
Keyphrases
- audio visual
- meta learning
- multi modal
- inductive learning
- visual information
- learning tasks
- speaker verification
- visual data
- multimedia
- model selection
- machine learning algorithms
- decision trees
- machine learning
- multi stream
- image representation
- data mining
- base classifiers
- transfer learning
- speech recognition
- information extraction