Cascade RNN-Transducer: Syllable Based Streaming On-device Mandarin Speech Recognition with a Syllable-to-Character Converter.
Xiong WangZhuoyuan YaoXian ShiLei XiePublished in: CoRR (2020)
Keyphrases
- speech recognition
- prosodic features
- speech synthesis
- language model
- n gram
- hidden markov models
- automatic speech recognition
- speech signal
- data conversion
- recurrent neural networks
- pattern recognition
- speaker independent
- noisy environments
- speech processing
- speech recognizer
- handwriting recognition
- speech retrieval
- isolated word
- speech recognition systems
- keyword spotting
- speaker identification
- text to speech
- speaker recognition
- speech recognition errors
- information retrieval