Audio Visual Speech Recognition using Deep Recurrent Neural Networks.
Abhinav ThandaShankar M. VenkatesanPublished in: CoRR (2016)
Keyphrases
- audio visual
- recurrent neural networks
- multi modal
- visual information
- neural network
- feed forward
- emotion recognition
- recurrent networks
- speaker verification
- multi stream
- reservoir computing
- echo state networks
- multimedia
- person authentication
- artificial neural networks
- visual data
- audio features
- audio visual speech recognition
- nonlinear dynamic systems
- text classification
- natural language processing
- nearest neighbor
- image data
- knowledge base
- computer vision
- machine learning