Optimising Speaker-Dependent Feature Extraction Parameters to Improve Automatic Speech Recognition Performance for People with Dysarthria.
Marco MariniNicola VanelloLuca FanucciPublished in: Sensors (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- speaker dependent
- phoneme recognition
- feature extraction
- speaker identification
- hidden markov models
- speaker adaptation
- speech signal
- broadcast news
- noisy environments
- speaker independent
- maximum likelihood
- feature space
- feature selection
- speech synthesis
- wavelet transform
- video data
- expectation maximization
- image classification
- language model