VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice Conversion.
Disong WangLiqun DengYu Ting YeungXiao ChenXunying LiuHelen MengPublished in: Interspeech (2021)
Keyphrases
- vector quantization
- speaker recognition
- image compression
- vector quantizer
- successive approximation
- reduced complexity
- distortion measure
- speech recognition
- fractal image coding
- input vector
- fractal image compression
- emotion recognition
- image representation
- image registration
- mutual information
- semi supervised
- multiscale
- computer vision
- unsupervised learning
- image processing
- speaker verification
- motion estimation
- video sequences
- codebook design