Domain adaptation for speech emotion recognition by sharing priors between related source and target classes.
Qirong MaoWentao XueQiyu RaoFeifei ZhangYongzhao ZhanPublished in: ICASSP (2016)
Keyphrases
- domain adaptation
- target domain
- source domain
- transfer learning
- multiple sources
- speech emotion recognition
- cross domain
- labeled data
- training data
- source and target domains
- domain specific
- training samples
- test data
- semi supervised
- unlabeled data
- manifold alignment
- semi supervised learning
- transfer knowledge
- sentiment classification
- data sources
- information sharing
- text categorization
- text classification
- covariate shift
- active learning