Dual-Decoder Transformer For end-to-end Mandarin Chinese Speech Recognition with Pinyin and Character.
Zhao YangWei XiRui WangRui JiangJizhong ZhaoPublished in: CoRR (2022)
Keyphrases
- end to end
- speech recognition
- chinese characters
- rate allocation
- error tolerant
- text input
- character recognition
- hidden markov models
- speech recognizer
- text localization and recognition
- pattern recognition
- automatic speech recognition
- speech signal
- language model
- speech synthesis
- speaker identification
- congestion control
- error concealment
- noisy environments
- graph matching
- error rate
- speech recognition systems
- scalable video
- optical character recognition
- image sequences
- probabilistic model
- feature extraction