Transformer-Based Online CTC/Attention End-To-End Speech Recognition Architecture.
Haoran MiaoGaofeng ChengChangfeng GaoPengyuan ZhangYonghong YanPublished in: ICASSP (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- speech signal
- real time
- speech synthesis
- language model
- automatic speech recognition
- admission control
- speaker identification
- noisy environments
- speech recognition technology
- pattern recognition
- network architecture
- speaker dependent
- speech recognition systems
- speech recognizer
- speaker independent
- machine learning
- congestion control
- application layer
- image processing
- cross layer
- mobile devices
- speech retrieval
- e learning
- audio visual speech recognition