Online Hybrid CTC/Attention Architecture for End-to-End Speech Recognition.
Haoran MiaoGaofeng ChengPengyuan ZhangTa LiYonghong YanPublished in: INTERSPEECH (2019)
Keyphrases
- end to end
- speech recognition
- language model
- hidden markov models
- speech processing
- real time
- pattern recognition
- speech signal
- speech recognition technology
- speech recognizer
- speech synthesis
- noisy environments
- online learning
- automatic speech recognition
- congestion control
- admission control
- machine learning
- speaker dependent
- speaker identification
- speech recognition systems
- speaker independent
- speech recognizers
- application layer
- multi channel
- computer vision
- network architecture
- image compression
- signal processing
- neural network