Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognition.
Shuai ZhangJiangyan YiZhengkun TianYe BaiJianhua TaoZhengqi WenPublished in: CoRR (2020)
Keyphrases
- end to end
- automatic speech recognition
- speech recognition
- spontaneous speech
- word error rate
- hidden markov models
- speech signal
- spoken words
- conversational speech
- noisy environments
- congestion control
- broadcast news
- admission control
- speech corpus
- acoustic models
- language model
- speech retrieval
- application layer
- high bandwidth
- speech recognizer
- real world
- spoken language
- pattern recognition
- scalable video
- neural network