The StarGANv2-VC model is a many-to-many non-parallel generative adversarial network (GAN) voice conversion (VC) that has proven effective in style tasks. This study aimed to investigate the scalability and diversity of for English emotional (EVC) across different speakers emotions. We carried out five experiments using an Emotional Speech Database (ESD), comprising single speaker-multi-emotion...

In the traditional voice conversion, converted speech is generated using statistical parametric models (for example Gaussian mixture model) whose parameters are estimated from parallel training utterances. A well-known problem of the statistical parametric methods is that statistical average in parameter estimation results in the over-smoothing of the speech parameter trajectories, and thus lea...

This paper presents a voice conversion technique based on bilinear models and introduces the concept of contextual modeling. The bilinear approach reformulates the spectral envelope representation from line spectral frequencies feature to a two-factor parameterization corresponding to speaker identity and phonetic information, the so-called style and content factors. This decomposition offers a...

To convert one speaker’s voice to another’s, the mapping of the corresponding speech segments from source speaker to target speaker must be obtained first. In parallel voice conversion, normally dynamic time warping (DTW) method is used to align signals of source and target voices. However, for conversion between non-parallel speech data, the DTW based mapping method does not work. In this pape...

Voice conversion (VC) technology allows to transform the voice of the source speaker so that it is perceived as the voice of a target speaker. One of the applications of VC is speech-to-speech translation where the voice has to inform, not only about what is said, but also about who is the speaker. This paper introduces the different methods submitted by UPC to the TC-STAR second evaluation cam...

Conventional approaches to voice conversion typically use a GMM to represent the joint probability density of source and target features. This model is then used to perform spectral conversion between speakers. This approach is reasonably effective but can be prone to overfitting and oversmoothing of the target spectra. This paper proposes an alternative scheme that uses a collection of Gaussia...