Speech synthesis method and related device, electronic equipment and storage medium

The invention discloses a speech synthesis method, a related device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-synthesized text and a reference speech of a target object; encoding based on a phoneme sequence of the text to be synthesized to obtain phoneme encoding features of each phoneme in the phoneme sequence, encoding based on the reference speech to obtain multi-scale speech features, and obtaining predicted pronunciation duration of each phoneme in the phoneme sequence; decoding based on the multi-scale speech features, the phoneme coding features of each phoneme and the predicted pronunciation duration to obtain a synthetic speech; wherein the multi-scale speech features comprise at least two of phoneme-level speech features, frame-level speech features and global speech features. According to the scheme, detail information such as pronunciation and rhythm of the target object can be reserved as much as possible in speech synthesis, and the similar