A Streaming End-to-End Speech Recognition Approach Based on WeNet for Tibetan Amdo Dialect.
Chao WangYao WenPhurba LhamoNyima TashiPublished in: MLNLP (2022)
Keyphrases
- end to end
- speech recognition
- scalable video
- rate adaptation
- hidden markov models
- speech synthesis
- data streams
- speech processing
- language model
- automatic speech recognition
- speech signal
- pattern recognition
- speech recognizer
- speech recognition systems
- noisy environments
- speaker identification
- content delivery
- congestion control
- transport protocol
- speaker dependent
- speech recognition technology
- stream processing
- neural network
- computer vision
- text localization and recognition
- audio visual speech recognition
- speaker independent
- feature extraction
- information retrieval