Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders.
Hok-Shing LauMark HuntlyNathon MorganAdesua IyenomaBiao ZengTim BashfordPublished in: CoRR (2024)
Keyphrases
- text to speech
- emotion recognition
- speech recognition
- statistical models
- audio visual
- automatic speech recognition
- voice activity detection
- speech signal
- probabilistic model
- speech recognition errors
- parameter estimation
- speech quality
- fundamental frequency
- speech synthesis
- speaker identification
- text to speech synthesis
- acoustic models
- multimodal interfaces
- language model
- semi automatic
- spoken language
- model selection
- noisy environments
- hidden markov models
- complex systems
- fully automatic
- statistical model