Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition.
Niko MoritzTakaaki HoriJonathan Le RouxPublished in: CoRR (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- hidden markov models
- speech synthesis
- speech signal
- speech processing
- language model
- speech recognizer
- pattern recognition
- bayesian networks
- rate adaptation
- speech recognition technology
- congestion control
- content delivery
- noisy environments
- automatic speech recognition
- speaker identification
- speech recognition systems
- neural network