Cross-corpus acoustic emotion recognition from singing and speaking: A multi-task learning approach.
Biqiao ZhangEmily Mower ProvostGeorg EsslPublished in: ICASSP (2016)
Keyphrases
- multi task learning
- emotion recognition
- emotional speech
- multi task
- learning tasks
- gaussian processes
- audio visual
- facial expressions
- learning problems
- sentiment analysis
- human computer interaction
- transfer learning
- emotion classification
- acoustic features
- information fusion
- high order
- theoretical analysis
- sentence level
- learning algorithm
- learning models
- facial images
- music information retrieval
- audio features
- image database
- emotional state
- affective states
- supervised learning
- support vector
- face recognition
- feature selection