DCT-Based Amplitude and Frequency Modulated Harmonic-Plus-Noise Modelling for Text-to-Speech Synthesis.
Kris HermusHugo Van hammeWerner VerhelstSufian IrhimehJan De MoortelPublished in: ICASSP (4) (2007)
Keyphrases
- text to speech synthesis
- low frequency
- frequency response
- random noise
- image compression
- high frequency
- signal to noise ratio
- noise level
- text to speech
- power spectra
- phase information
- noise model
- missing data
- additive noise
- image noise
- instantaneous frequency
- wavelet transform
- noise free
- image structure
- frequency domain
- post processing
- optical flow
- dct domain
- power spectrum
- discrete cosine transform
- high pass