Compensating for speaker or lexical variabilities in speech for emotion recognition.
Soroosh MariooryadCarlos BussoPublished in: Speech Commun. (2014)
Keyphrases
- emotion recognition
- audio visual
- speaker verification
- emotional speech
- speaker recognition
- multi modal
- human computer interaction
- wordnet
- visual information
- emotion classification
- facial expressions
- natural language processing
- multi stream
- acoustic features
- speech recognition
- emotional state
- information fusion
- facial images
- visual data
- machine learning
- semantic relations
- sentiment analysis
- software engineering
- lexical features
- multimedia
- automatic speech recognition
- affective states
- speaker identification
- intelligent agents
- image classification
- speaker diarization
- computer vision