High-level feature representation using recurrent neural network for speech emotion recognition.
Jinkyu LeeIvan TashevPublished in: INTERSPEECH (2015)
Keyphrases
- feature representation
- recurrent neural networks
- speech emotion recognition
- high level
- low level
- feature extraction
- feed forward
- feature representations
- complex valued
- low dimensional
- neural network
- feature set
- hidden layer
- artificial neural networks
- recurrent networks
- low level features
- echo state networks
- reservoir computing
- face recognition
- sparse representation
- face detection
- data mining
- pattern recognition
- decision trees
- image processing
- neural network structure
- computer vision