Streaming End-to-End Speech Recognition with Jointly Trained Neural Feature Enhancement.
Chanwoo KimAbhinav GargDhananjaya GowdaSeongkyu MunChangwoo HanPublished in: ICASSP (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- isolated word
- language model
- hidden markov models
- speech signal
- automatic speech recognition
- cepstral coefficients
- speech recognizer
- rate adaptation
- speech synthesis
- pattern recognition
- speech processing
- speech recognition systems
- speech recognition technology
- network architecture
- congestion control
- speaker independent
- image processing
- speaker identification
- noisy environments
- neural network
- feature vectors
- data streams
- feature set
- speaker dependent
- feature extraction