Segment-based speech emotion recognition using recurrent neural networks.
Efthymios TzinisAlexandros PotamianosPublished in: ACII (2017)
Keyphrases
- recurrent neural networks
- emotion recognition
- text to speech synthesis
- emotional state
- emotional speech
- feed forward
- neural network
- feedforward neural networks
- speech recognition
- speech segments
- artificial neural networks
- complex valued
- facial expressions
- reservoir computing
- recurrent networks
- long short term memory
- neural model
- audio visual
- speech signal
- echo state networks
- text to speech
- hebbian learning
- cascade correlation
- human computer interaction
- artificial intelligence
- machine learning
- broadcast news
- emotion classification
- nonlinear dynamic systems
- long term