Speaker-independent classification of phonetic segments from raw ultrasound in child speech.
Manuel Sam RibeiroAciel EshkyKorin RichmondSteve RenalsPublished in: CoRR (2019)
Keyphrases
- speech recognition
- speaker independent
- emotion classification
- digit recognition
- hidden markov models
- speaker dependent
- pattern recognition
- speech recognizer
- speaker identification
- speech recognition systems
- speech signal
- feature extraction
- speech synthesis
- noisy environments
- image classification
- support vector machine
- classification accuracy
- feature vectors
- spoken language
- feature selection
- automatic speech recognition
- language model
- low level
- acoustic models
- speaker adaptation
- neural network
- emotional speech
- hand written
- generative model
- model selection
- text classification
- feature space