Gradient-Based Dimensionality Reduction for Speech Emotion Recognition Using Deep Networks.
Hongxuan WangPrahlad VadakkepatPublished in: ICASSP (2024)
Keyphrases
- dimensionality reduction
- emotion recognition
- text to speech synthesis
- high dimensional
- high dimensionality
- structure preserving
- data representation
- speech recognition
- emotional state
- feature extraction
- computer networks
- network structure
- principal component analysis
- neural network
- facial expressions
- high dimensional data
- low dimensional
- principal components
- audio visual
- network design
- pattern recognition and machine learning
- linear dimensionality reduction
- recognition engine
- computer vision
- spoken language
- face recognition
- heterogeneous networks
- feature space
- data points
- automatic speech recognition
- data sets
- linear discriminant analysis