Multi-Source Discriminant Subspace Alignment for Cross-Domain Speech Emotion Recognition.
Shaokai LiPeng SongWenming ZhengPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2023)
Keyphrases
- cross domain
- multi source
- speech emotion recognition
- discriminant subspace
- data fusion
- discriminant analysis
- information fusion
- multiple sources
- knowledge transfer
- transfer learning
- data sources
- data integration
- subspace learning
- text categorization
- domain adaptation
- artificial intelligence
- e government
- data warehouse
- decision making
- databases
- text classification
- pattern recognition
- face recognition
- database systems
- case study