A Practical Two-Stage Training Strategy for Multi-Stream End-to-End Speech Recognition.
Ruizhi LiGregory SellXiaofei WangShinji WatanabeHynek HermanskyPublished in: ICASSP (2020)
Keyphrases
- end to end
- audio visual speech recognition
- multi stream
- speech recognition
- hidden markov models
- audio visual
- isolated word
- language model
- acoustic models
- congestion control
- automatic speech recognition
- noisy environments
- pattern recognition
- speech signal
- discriminative training
- speech synthesis
- machine learning
- speaker identification
- speech recognizer
- training set
- neural network
- multi modal
- high dimensional
- speech recognition systems
- speaker independent