Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes.
Bo LiYu ZhangTara N. SainathYonghui WuWilliam ChanPublished in: ICASSP (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- pattern recognition
- speech recognizer
- speech synthesis
- speech processing
- noisy environments
- speech recognition technology
- speech signal
- speech recognition systems
- automatic speech recognition
- speaker identification
- speaker independent
- digital libraries
- congestion control
- language independent
- natural language processing
- feature vectors
- audio visual speech recognition