Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition.
Xinyuan ZhouEmre YilmazYanhua LongYijie LiHaizhou LiPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- error control
- video codec
- low complexity
- decoding process
- distributed video coding
- speech signal
- error correction
- hidden markov models
- speech synthesis
- speech processing
- language model
- turbo codes
- speech recognizer
- speech recognition technology
- pattern recognition
- automatic speech recognition
- speaker identification
- speaker independent
- speech recognizers
- speaker dependent
- error resilience
- noisy environments
- wyner ziv
- rate distortion
- bit rate
- video coding
- isolated word
- neural network
- audio visual speech recognition
- video transmission
- error concealment
- variable length
- video quality
- image processing