Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition.
Shujie HuXurong XieMengzhe GengZengrui JinJiajun DengGuinan LiYi WangMingyu CuiTianzi WangHelen MengXunying LiuPublished in: CoRR (2024)
Keyphrases
- speech recognition
- automatic speech recognition
- speech recognition systems
- hidden markov models
- acoustic models
- speech processing
- cepstral coefficients
- speech synthesis
- speech understanding
- noisy environments
- pattern recognition
- speech signal
- language model
- speaker identification
- speech recognizer
- speech recognition technology
- probabilistic model
- feature set
- mel frequency cepstral coefficients
- speech retrieval
- speech recognition errors
- feature extraction
- speaker independent
- feature vectors
- keyword spotting
- word error rate
- speech recognizers
- handwriting recognition
- audio visual speech recognition
- feature space
- extracting features
- model selection