WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit.
Binbin ZhangDi WuZhendong PengXingchen SongZhuoyuan YaoHang LvLei XieChao YangFuping PanJianwei NiuPublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech recognizer
- speech synthesis
- automatic speech recognition
- speech signal
- pattern recognition
- language model
- speaker identification
- speech recognition technology
- noisy environments
- speech processing
- speech recognition systems
- congestion control
- speaker independent
- isolated word
- text localization and recognition
- machine learning
- motion estimation
- probabilistic model
- multimedia
- computer vision
- speaker dependent
- real world
- neural network