Speaker adaptation for Wav2vec2 based dysarthric ASR.
Murali Karthick BaskarTim HerzigDiana NguyenMireia DíezTim PolzehlLukás BurgetJan Honza CernockýPublished in: CoRR (2022)
Keyphrases
- speaker adaptation
- automatic speech recognition
- speech recognition
- hidden markov models
- speech signal
- broadcast news
- speaker independent
- acoustic features
- noisy environments
- language model
- speech recognizer
- pattern recognition
- non stationary
- neural network
- speech synthesis
- speech recognition systems
- image processing