Voice conversion training method and server and computer readable storage medium

A server comprising an obtaining circuit, a processor, and a memory, wherein the processor is coupled to the memory and the obtaining circuit, the memory stores one or more computer programs executable on the processor;

• wherein the one or more computer programs comprise:
• instructions for forming a first training data set, wherein the first training data set comprises a plurality of training voice data groups;
• instructions for selecting two of the training voice data groups from the first training data set to input into a voice conversion neural network for training;
• instructions for forming a second training data set, wherein the second training set comprises the first training data set and a first source speaker voice data group;
• instructions for inputting one of the training voice data groups selected from the first training data set and the first source speaker voice data group into the voice conversion neural network for training;
• instructions for forming a third training data set, wherein the third training data set comprises a second source speaker voice data group and a personalized voice data group, the second source speaker voice data group comprises a second quantity of second source speaker voice data and corresponds to a same speaker with the first source speaker voice data group, and the personalized voice data group comprises the second quantity of personalized voice data;
• wherein the personalized voice data group is obtained from a terminal device;
• instructions for inputting the second source speaker voice data group and the personalized voice data group are into the voice conversion neural network for training;
• instructions for obtaining to-be-converted voice data, wherein the to-be-converted voice data corresponds to a same speaker with the personalized voice data group;
• and
• instructions for inputting the to-be-converted voice data into the voice conversion neural network, and obtaining target voice data based on an output of the voice conversion neural network.

A non-transitory computer-readable storage medium storing one or more computer programs executable on a processor to implement a face recognition method, wherein the one or more computer programs comprise:

• instructions for forming a first training data set, wherein the first training data set comprises a plurality of training voice data groups;
• instructions for selecting two of the training voice data groups from the first training data set to input into a voice conversion neural network for training;
• instructions for forming a second training data set, wherein the second training set comprises the first training data set and a first source speaker voice data group;
• instructions for inputting one of the training voice data groups selected from the first training data set and the first source speaker voice data group into the voice conversion neural network for training;
• instructions for forming a third training data set, wherein the third training data set comprises a second source speaker voice data group and a personalized voice data group, the second source speaker voice data group comprises a second quantity of second source speaker voice data and corresponds to a same speaker with the first source speaker voice data group, and the personalized voice data group comprises the second quantity of personalized voice data;
• wherein the personalized voice data group is obtained from a terminal device;
• instructions for inputting the second source speaker voice data group and the personalized voice data group are into the voice conversion neural network for training;
• instructions for obtaining to-be-converted voice data, wherein the to-be-converted voice data corresponds to a same speaker with the personalized voice data group;
• and
• instructions for inputting the to-be-converted voice data into the voice conversion neural network, and obtaining target voice data based on an output of the voice conversion neural network.