Lifter Training and Sub-Band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials.
Takaaki SaekiYuki SaitoShinnosuke TakamichiHiroshi SaruwatariPublished in: ICASSP (2020)
Keyphrases
- subband
- computationally efficient
- high quality
- filter bank
- discrete wavelet transform
- wavelet transform
- high frequency
- multiresolution
- low frequency
- image compression
- low pass
- frequency domain
- locally adaptive
- wavelet coefficients
- wavelet decomposition
- wavelet domain
- feature vectors
- image quality
- machine learning
- contourlet transform
- wavelet packet
- bit rate
- high resolution
- image processing