Enhancing a glossectomy patient's speech via GMM-based voice conversion.
Kei TanakaSunao HaraMasanobu AbeShogo MinagiPublished in: APSIPA (2016)
Keyphrases
- voice activity detection
- noisy environments
- speaker recognition
- speech recognition
- mel frequency cepstral coefficients
- speaker identification
- gaussian mixture model
- text to speech
- speech synthesis
- patient data
- medical treatment
- speech signal
- clinical data
- speech recognition errors
- speech quality
- clinical trials
- emotion recognition
- medical data
- fundamental frequency
- clinical practice
- prosodic features
- electronic health records
- speaker verification
- linear predictive
- broadcast news
- intensive care
- video sequences
- heart rate
- noise reduction
- medical images
- hidden markov models