Fast variable-frame-rate decoding of speech recognition based on deep neural networks.
Ge ZhangPengyuan ZhangJielin PanYonghong YanPublished in: ICNC-FSKD (2017)
Keyphrases
- speech recognition
- frame rate
- neural network
- pattern recognition
- video sequences
- video camera
- high speed
- hidden markov models
- automatic speech recognition
- language model
- speech signal
- speech recognition technology
- speech processing
- video quality
- noisy environments
- speech synthesis
- speech recognition systems
- d scene
- speech recognizer
- speaker independent
- speaker identification
- speech recognizers
- isolated word
- speech retrieval
- motion blur
- audio visual speech recognition