Breathy to Tense Voice Discrimination using Zero-Time Windowing Cepstral Coefficients (ZTWCCs).
Sudarsana Reddy KadiriBayya YegnanarayanaPublished in: INTERSPEECH (2018)
Keyphrases
- image processing
- cepstral coefficients
- speech recognition
- mel frequency cepstral coefficients
- linear predictive
- feature set
- speech signal
- speaker identification
- linear prediction
- gaussian mixture model
- speaker recognition
- principal component analysis
- feature vectors
- acoustic features
- audio signal
- feature selection
- spectral features
- remote sensing
- automatic speech recognition
- speaker verification
- text to speech
- multiresolution
- image compression