Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech.
Shijun WangJón GuðnasonDamian BorthPublished in: CoRR (2023)
Keyphrases
- text to speech
- data sets
- prior knowledge
- data analysis
- speech emotion recognition
- word processing
- multiple representations
- data sources
- online learning
- high dimensional data
- data points
- speech synthesis
- speech recognition
- data collection
- active learning
- data structure
- learning tasks
- learning process
- learning environment
- training data
- feature selection