Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture.
Takafumi MoriyaTomohiro TanakaTakanori AshiharaTsubasa OchiaiHiroshi SatoAtsushi AndoRyo MasumuraMarc DelcroixTaichi AsamiPublished in: Interspeech (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- hidden markov models
- rate adaptation
- language model
- cross layer
- real time
- automatic speech recognition
- speech synthesis
- pattern recognition
- speech processing
- speech recognizer
- speech signal
- noisy environments
- speech recognition technology
- speaker independent
- congestion control
- differentiated services
- data streams
- speech recognition systems
- speaker identification
- content delivery
- isolated word
- transport layer
- machine learning
- neural network