Speech synthesis method and device, computer equipment and storage medium

The invention relates to a speech synthesis method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring reading emotion information when a source speaking object reads voice data; fusing the reading emotion information and the tone information corresponding to the target speaking object to obtain a tone emotion fusion vector; obtaining a phoneme vector sequence corresponding to a speech text to be synthesized, and inputting the tone emotion fusion vector and the phoneme vector sequence into an emotion transfer speech synthesis model to obtain emotion transfer speech; wherein the emotion migration voice comprises the voice of the target speaking object reading the to-be-synthesized voice text according to the reading emotion of the source speaking object. By adopting the method, the synthesis efficiency of the emotional speech can be effectively improved. 本申请涉及一种语音合成方法、装置、计算机设备、存储介质和计算机程序产品。所述方法包括：获取源说话对象朗读语音数据时的朗读情感信息；对所述朗读情感信息和目标