Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network.
George TrigeorgisFabien RingevalRaymond BruecknerErik MarchiMihalis A. NicolaouBjörn W. SchullerStefanos ZafeiriouPublished in: ICASSP (2016)
Keyphrases
- end to end
- recurrent networks
- unsupervised feature learning
- admission control
- speech recognition
- deep learning
- ad hoc networks
- emotional speech
- emotional state
- congestion control
- high bandwidth
- emotion recognition
- emotion classification
- feature vectors
- wireless ad hoc networks
- multipath
- neural network
- text to speech synthesis
- content delivery