Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin.
Linhao DongShiyu ZhouWei ChenBo XuPublished in: CoRR (2018)
Keyphrases
- end to end
- speech recognition
- scalable video
- rate adaptation
- speaker independent
- hidden markov models
- language model
- pattern recognition
- automatic speech recognition
- speech recognizer
- data streams
- speech processing
- speech recognition technology
- noisy environments
- speech signal
- speech synthesis
- video streaming
- network architecture
- content delivery
- congestion control
- speaker identification
- speech recognition systems
- transport protocol
- broadcast news
- image processing
- speaker dependent