Audio Visual Speech Recognition Using Deep Recurrent Neural Networks.
Abhinav ThandaShankar M. VenkatesanPublished in: MPRSS (2016)
Keyphrases
- audio visual
- recurrent neural networks
- multi modal
- visual information
- multi stream
- neural network
- emotion recognition
- feed forward
- recurrent networks
- reservoir computing
- multimedia
- person authentication
- echo state networks
- audio features
- audio visual speech recognition
- artificial neural networks
- visual data
- speaker verification
- data sets
- feature space
- knowledge base
- feature selection
- machine learning