Weakly-Supervised Multi-Task Learning for Audio-Visual Speaker Verification.
Anith SelvakumarHoma FashandiPublished in: CoRR (2023)
Keyphrases
- speaker verification
- audio visual
- multi task
- multi modal
- feature selection
- emotion recognition
- multi class
- visual information
- multimedia
- visual data
- transfer learning
- topic models
- pairwise
- support vector machine
- data sets
- nearest neighbor
- image representation
- image features
- information extraction
- image data
- data analysis
- learning algorithm