Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames.
Chengdong LiangXiao-Lei ZhangBinbin ZhangDi WuShengqiang LiXingchen SongZhendong PengFuping PanPublished in: ICASSP (2023)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- language model
- speech synthesis
- automatic speech recognition
- speech signal
- speaker identification
- speech recognition systems
- congestion control
- speaker independent
- speech recognizer
- isolated word
- speech recognizers
- speech recognition technology
- noisy environments
- pattern recognition
- vector quantization
- neural network