Long-Term Statistical Feature Extraction from Speech Signal and Its Application in Emotion Recognition.
Erfan LoweimiMortaza DoulatyJon BarkerThomas HainPublished in: SLSP (2015)
Keyphrases
- emotion recognition
- speech signal
- feature extraction
- speaker identification
- speaker verification
- speech recognition
- speaker recognition
- mel frequency cepstral coefficients
- cepstral coefficients
- emotional speech
- audio visual
- automatic speech recognition
- emotion classification
- facial expressions
- human computer interaction
- noisy environments
- acoustic features
- hidden markov models
- non stationary
- fundamental frequency
- spectral analysis
- information fusion
- image processing
- sentiment analysis
- image classification
- speech quality
- language model
- feature space
- face recognition
- emotional state
- facial images
- noisy images
- data fusion
- principal component analysis
- feature vectors
- pattern recognition
- feature selection