Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels
This work addresses voice conversion for emotional expression, presenting an incremental improvement with a novel network architecture.
The paper tackles the problem of F0 transformation for expressive voice conversion by proposing an end-to-end framework using a single neural network with a convolutional wavelet kernel module for multi-scale F0 representation and an adversarial module for emotion transformation, achieving results directly from raw F0 signals.
This paper presents a end-to-end framework for the F0 transformation in the context of expressive voice conversion. A single neural network is proposed, in which a first module is used to learn F0 representation over different temporal scales and a second adversarial module is used to learn the transformation from one emotion to another. The first module is composed of a convolution layer with wavelet kernels so that the various temporal scales of F0 variations can be efficiently encoded. The single decomposition/transformation network allows to learn in a end-to-end manner the F0 decomposition that are optimal with respect to the transformation, directly from the raw F0 signal.