WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit.
Zhuoyuan YaoDi WuXiong WangBinbin ZhangFan YuChao YangZhendong PengXiaoyu ChenLei XieXin LeiPublished in: Interspeech (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- rate adaptation
- data streams
- hidden markov models
- language model
- speech synthesis
- speech signal
- speech processing
- pattern recognition
- speech recognizer
- video streaming
- speaker identification
- application layer
- speech recognition systems
- automatic speech recognition
- transport protocol
- speech recognition technology
- real time
- congestion control
- cross layer
- speech recognizers
- isolated word
- content delivery
- speaker independent
- machine learning
- noisy environments
- mobile devices
- multimedia
- speaker dependent
- computer vision
- information retrieval