Voice conversion method and device, electronic equipment and storage medium

The embodiment of the invention discloses a voice conversion method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring first voice data of a source speaker and second voice data of a target speaker; extracting a first linear spectrum from the first voice data, and extracting a first speaker vector from the second voice data; encoding the first linear spectrum to obtain first content distribution of the first voice data; performing distribution transformation on the first content distribution according to the first speaker vector to obtain second content distribution; and reconstructing voice data of the target speaker according to the first speaker vector and the second content distribution. 本实施例公开了一种语音转换方法、装置、电子设备和存储介质，该方法包括：获取源说话人的第一语音数据和目标说话人的第二语音数据；对所述第一语音数据提取第一线性谱，对所述第二语音数据提取第一说话人向量；通过对所述第一线性谱进行编码，得出所述第一语音数据的第一内容分布；根据所述第一说话人向量，对所述第一内容分布进行变换分布，得到第二内容分布；根据所述第一说话人向量和所述第二内容分布，重构所述目标说话人的语音数据。