Sound conversion model training method, electronic equipment and storage medium

The invention discloses a sound conversion model training method, electronic equipment and a storage medium. The method comprises the steps that: first training voice data is acquired from a first voice data set, the first voice data set comprises multiple pieces of voice data of a target speaker, and the first training voice data corresponds to a first acoustic feature; a posterior probability feature corresponding to the first acoustic feature is obtained; the posterior probability feature corresponding to the first acoustic feature and a first auxiliary timbre feature are inputted into a sound conversion model to obtain a first parallel feature; a posterior probability feature corresponding to the first parallel feature is obtained; the posterior probability feature corresponding to the first parallel feature and a target timbre feature are inputted into the sound conversion model to obtain a second acoustic feature; the parameters of the sound conversion model are adjusted based on a difference between th