Multi-encoder multi-resolution framework for end-to-end speech recognition.
Ruizhi LiXiaofei WangSri Harish Reddy MallidiTakaaki HoriShinji WatanabeHynek HermanskyPublished in: CoRR (2018)
Keyphrases
- bit rate
- end to end
- speech recognition
- multiresolution
- image quality
- coding efficiency
- hidden markov models
- pattern recognition
- speech synthesis
- speech processing
- neural network
- automatic speech recognition
- language model
- speech signal
- speech recognition technology
- audio visual speech recognition
- speech recognition systems
- speech recognizer
- probabilistic model
- bayesian networks