Voice conversion (VC) systems fall into two families: non-parametric embedding-space methods, which need no trained model but degrade on short target utterances, and spectrogram-based neural architectures, which achieve strong quality via multi-module pipelines with tens of millions of parameters. We propose kNN-FM-VC,...
Analysis using speaker similarity, Fr\'echet Audio Distance, and visualization of embedding distributions suggests that DOT succeeds by shifting source speech toward bona fide regions of the representation space rather than by maximizing speaker similarity.
A. Selitskiy, Akib Shahriyar, Jishnuraj Prakasan· arXiv.org· 0 citations
This paper shows that the semi-dual formulation of the optimal transport problem has a degenerate saddle-point structure, and that its numerical solution is equivalent to solving a constrained optimization problem. We derive necessary and sufficient conditions for the convergence of Monge maps without requiring optimal...
A. Selitskiy, David Millard· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.