Multi-Stream End-to-End Speech Recognition.
Ruizhi LiXiaofei WangSri Harish MallidiShinji WatanabeTakaaki HoriHynek HermanskyPublished in: CoRR (2019)
Keyphrases
- end to end
- multi stream
- speech recognition
- audio visual speech recognition
- hidden markov models
- audio visual
- speech recognizer
- language model
- automatic speech recognition
- speech synthesis
- speech signal
- noisy environments
- computer vision
- pattern recognition
- speech recognition systems
- probabilistic model
- high dimensional
- information retrieval
- speaker identification
- face recognition