Simulating Dysarthric Speech for Training Data Augmentation in Clinical Speech Applications.
Yishan JiaoMing TuVisar BerishaJulie LissPublished in: ICASSP (2018)
Keyphrases
- training data
- speech recognition
- speech signal
- speech synthesis
- audio visual
- automatic speech recognition
- recognition engine
- pattern recognition
- dialogue system
- emotion recognition
- spoken language
- speaker identification
- supervised learning
- test set
- multimodal interfaces
- text to speech
- hearing impaired
- training set
- decision trees
- human computer interaction
- domain knowledge
- hidden markov models