Voice conversion method and device, equipment, storage medium and program product

The invention relates to a voice conversion method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring original semantic features corresponding to voice data to be converted; adjusting the voice length corresponding to the original semantic feature through alignment information to obtain a target semantic feature; the alignment information is generated according to a mapping relation between a plurality of original semantic features and corresponding standard semantic features; and determining target voice data converted from the to-be-converted voice data through the target semantic feature. By adopting the method, the voice conversion speed can be increased. 本申请涉及一种语音转换方法、装置、设备、存储介质和程序产品。所述方法包括：获取待转换语音数据对应的原始语义特征；通过对齐信息将所述原始语义特征对应的语音长度进行调整，获得目标语义特征；所述对齐信息为根据多个原始语义特征和对应的标准语义特征之间的映射关系生成；通过所述目标语义特征确定所述待转换语音数据转换后的目标语音数据。采用本方法能够加快语音转换速度。