Streaming End-to-end Speech Recognition for Mobile Devices.
Yanzhang HeTara N. SainathRohit PrabhavalkarIan McGrawRaziel AlvarezDing ZhaoDavid RybachAnjuli KannanYonghui WuRuoming PangQiao LiangDeepti BhatiaYuan ShangguanBo LiGolan PundakKhe Chai SimTom BagbyShuo-Yiin ChangKanishka RaoAlexander GruensteinPublished in: ICASSP (2019)
Keyphrases
- end to end
- speech recognition
- mobile devices
- scalable video
- rate adaptation
- speech recognition technology
- hidden markov models
- mobile learning
- context aware
- automatic speech recognition
- speech synthesis
- language model
- mobile phone
- pattern recognition
- speech recognizer
- data streams
- speech processing
- speech signal
- speech recognition systems
- noisy environments
- mobile users
- congestion control
- transport protocol
- speaker identification
- probabilistic model
- neural network
- video streaming
- location aware
- transport layer
- speaker independent