Improving Speaker-Independent Speech Emotion Recognition using Dynamic Joint Distribution Adaptation.
Cheng LuYuan ZongHailun LianYan ZhaoBjörn W. SchullerWenming ZhengPublished in: ICASSP (2024)
Keyphrases
- joint distribution
- speech recognition
- speaker independent
- speaker adaptation
- speaker dependent
- emotion classification
- hidden markov models
- random variables
- emotional speech
- digit recognition
- speaker identification
- conditional probabilities
- speech recognizer
- automatic speech recognition
- emotion recognition
- maximum entropy
- speech recognition systems
- marginal distributions
- language model
- speech signal
- maximum likelihood
- bayesian networks
- multi modal
- acoustic models
- emotional state
- natural language