Speech emotion recognition based on formant characteristics feature extraction and phoneme type convergence.
Zhentao LiuAbdul RehmanMin WuWeihua CaoMan HaoPublished in: Inf. Sci. (2021)
Keyphrases
- speech emotion recognition
- feature extraction
- speech recognition
- automatic speech recognition
- texture features
- convergence rate
- feature vectors
- discriminant analysis
- pattern recognition
- multiresolution
- hidden markov models
- principal component analysis
- real time
- feature representation
- image classification
- preprocessing
- face recognition
- neural network
- database
- wavelet transform
- support vector machine
- video sequences
- texture analysis
- speech signal
- feature selection