Pronunciation-Aware Unique Character Encoding for RNN Transducer-Based Mandarin Speech Recognition.
Peng ShenXugang LuHisashi KawaiPublished in: SLT (2022)
Keyphrases
- speech recognition
- speaker independent
- recurrent neural networks
- hidden markov models
- automatic speech recognition
- language model
- pattern recognition
- speech processing
- speaker identification
- speech synthesis
- speech recognizer
- speech signal
- speech recognition systems
- speaker dependent
- speech recognition technology
- machine learning
- speech recognizers
- noisy environments
- variable length
- isolated word
- handwriting recognition
- maximum likelihood
- neural network