Audio visual speech recognition with multimodal recurrent neural networks.
Weijiang FengNaiyang GuanYuan LiXiang ZhangZhigang LuoPublished in: IJCNN (2017)
Keyphrases
- recurrent neural networks
- audio visual speech recognition
- multi stream
- audio visual
- neural network
- multi modal
- hidden markov models
- echo state networks
- feed forward
- neural model
- recurrent networks
- cascade correlation
- reservoir computing
- visual speech
- artificial neural networks
- speech recognition
- nonlinear dynamic systems
- artificial intelligence
- visual data
- image retrieval