Fundamental frequency and voicing prediction from MFCCs for speech reconstruction from unconstrained speech.
Ben MilnerXu ShaoJonathan DarchPublished in: INTERSPEECH (2005)
Keyphrases
- fundamental frequency
- speech recognition
- speech signal
- speaker recognition
- linear prediction
- automatic speech recognition
- acoustic features
- speech synthesis
- mel frequency cepstral coefficients
- cepstral coefficients
- hidden markov models
- audio features
- noisy environments
- speaker identification
- spoken language
- prediction error
- image reconstruction
- three dimensional
- neural network
- dialogue system
- speaker verification
- audio visual
- text to speech
- multiresolution
- pattern recognition