Singing synthesis method and device for generating personalized timbre and storage medium

The invention relates to the technical field of voice signal processing and artificial intelligence, in particular to a singing synthesis method and device for generating personalized timbre and a storage medium, and the method comprises the steps: obtaining historical acoustic feature data, building an acoustic feature training model, and obtaining a singing feature training model; training the acoustic feature training model through the historical acoustic feature data to obtain a trained acoustic feature training model; the method comprises the following steps: inputting set acoustic characteristic data, preprocessing to obtain a phoneme data sequence, expanding phonemes according to the duration of the phonemes to form a phoneme expansion sequence, and processing the phoneme expansion sequence to enable the length of the phoneme expansion sequence to be consistent with the length of the set acoustic characteristic data. The phoneme data sequence comprises the duration time and pitch of each phoneme, the p