Decoupling Pronunciation and Language for End-to-End Code-Switching Automatic Speech Recognition.
Shuai ZhangJiangyan YiZhengkun TianYe BaiJianhua TaoZhengqi WenPublished in: ICASSP (2021)
Keyphrases
- end to end
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- spontaneous speech
- hidden markov models
- spoken words
- high bandwidth
- broadcast news
- speech retrieval
- conversational speech
- language model
- speech corpus
- congestion control
- acoustic models
- language processing
- natural language
- discriminative training
- transport layer
- admission control
- noisy environments
- non stationary
- bayesian networks