Pronunciation-aware unique character encoding for RNN Transducer-based Mandarin speech recognition.
Peng ShenXugang LuHisashi KawaiPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speaker independent
- recurrent neural networks
- hidden markov models
- speech synthesis
- speech processing
- speech recognizer
- speech signal
- automatic speech recognition
- pattern recognition
- language model
- speech recognition technology
- handwriting recognition
- noisy environments
- speech recognizers
- speaker identification
- isolated word
- speech retrieval
- speaker dependent
- speech recognition systems
- speaker recognition
- optical character recognition