Improving Audio-Visual Speech Recognition Using Gabor Recurrent Neural Networks.
Ali S. SaudiMahmoud I. KhalilHazem M. AbbasPublished in: MPRSS (2018)
Keyphrases
- recurrent neural networks
- visual speech
- audio visual speech recognition
- hidden markov models
- visual speech recognition
- feed forward
- speaker identification
- neural network
- echo state networks
- audio signals
- recurrent networks
- noisy environments
- artificial neural networks
- audio signal
- broadcast news
- speech signal
- face recognition
- text to speech
- audio visual
- multi stream
- gabor filters
- multimedia
- acoustic features
- multiresolution