Cascade RNN-Transducer: Syllable Based Streaming On-Device Mandarin Speech Recognition with a Syllable-To-Character Converter.
Xiong WangZhuoyuan YaoXian ShiLei XiePublished in: SLT (2021)
Keyphrases
- speech recognition
- speech synthesis
- prosodic features
- language model
- n gram
- speaker independent
- hidden markov models
- speech processing
- pattern recognition
- speech signal
- recurrent neural networks
- speech recognition technology
- data conversion
- speaker identification
- automatic speech recognition
- speech recognizer
- keyword spotting
- speech recognition systems
- speech recognizers
- word level
- handwriting recognition
- cepstral coefficients
- noisy environments
- text to speech
- speech recognition errors
- speech retrieval
- machine learning