Combining speech recognition and acoustic word emotion models for robust text-independent emotion recognition.
Björn W. SchullerBogdan VlasenkoDejan ArsicGerhard RigollAndreas WendemuthPublished in: ICME (2008)
Keyphrases
- speech recognition
- emotion recognition
- speech recognition systems
- acoustic models
- emotional speech
- speech recognizer
- speech recognizers
- speaker independent
- emotion classification
- noisy environments
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- audio visual
- pattern recognition
- probabilistic model
- speaker verification
- facial expressions
- information retrieval
- speech synthesis
- speaker identification
- human computer interaction
- neural network
- broadcast news
- speaker recognition
- n gram
- emotional state
- sentiment analysis
- keywords
- information fusion
- sentence level
- natural language
- multimedia