Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition.
Niko MoritzTakaaki HoriJonathan Le RouxPublished in: Interspeech (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- speech processing
- hidden markov models
- speech synthesis
- speech recognizer
- bayesian networks
- noisy environments
- speech signal
- language model
- speech recognition systems
- speaker identification
- pattern recognition
- rate adaptation
- speaker independent
- congestion control
- speech recognition technology
- application layer
- speech retrieval
- content delivery
- text localization and recognition
- audio visual speech recognition
- neural network
- data streams
- image processing