Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition.
Mengzhe GengXurong XieZi YeTianzi WangGuinan LiShujie HuXunying LiuHelen MengPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speaker adaptation
- speech recognition systems
- speech recognizer
- hidden markov models
- speaker dependent
- speaker independent
- automatic speech recognition
- language model
- pattern recognition
- noisy environments
- speaker identification
- low level
- maximum likelihood
- speech synthesis
- mel frequency cepstral coefficients
- feature vectors
- feature space
- feature extraction
- speech signal
- natural language processing