Recurrent Neural Network Transducer for Audio-Visual Speech Recognition.
Takaki MakinoHank LiaoYannis M. AssaelBrendan ShillingfordBasilio GarciaOtavio BragaOlivier SiohanPublished in: ASRU (2019)
Keyphrases
- recurrent neural networks
- audio visual speech recognition
- multi stream
- audio visual
- neural network
- complex valued
- feed forward
- reservoir computing
- recurrent networks
- artificial neural networks
- echo state networks
- noisy environments
- neural model
- speech recognition
- emotion recognition
- speaker verification
- audio signal
- multi modal
- information retrieval systems
- high level