Staged Knowledge Distillation for End-to-End Dysarthric Speech Recognition and Speech Attribute Transcription.
Yuqin LinLongbiao WangSheng LiJianwu DangChenchen DingPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- end to end
- speech recognition technology
- speech recognition systems
- speech synthesis
- handwriting recognition
- speech signal
- speech recognizer
- hidden markov models
- automatic speech recognition
- language model
- speech processing
- pattern recognition
- speaker identification
- noisy environments
- keyword spotting
- recognition engine
- speaker independent
- speech recognizers
- isolated word
- speaker dependent
- congestion control
- speaker diarization
- word error rate
- speaker recognition
- cepstral coefficients
- audio visual speech recognition
- neural network
- speech recognition errors
- spoken language
- mobile devices
- image processing
- machine learning