Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition.
Shujie HuXurong XieZengrui JinMengzhe GengYi WangMingyu CuiJiajun DengXunying LiuHelen MengPublished in: CoRR (2023)
Keyphrases
- speech recognition
- automatic speech recognition
- language model
- acoustic models
- speech signal
- noisy environments
- hidden markov models
- pre trained
- speech recognizer
- speech synthesis
- speech recognition technology
- word error rate
- speaker identification
- probabilistic model
- pattern recognition
- neural network
- signal processing
- feature selection
- speaker dependent
- speech retrieval