Self-adaptive speech synthesis method and device

The invention discloses a self-adaptive speech synthesis method and device. The method comprises the steps: training a preset neural network model through a preset recording and text annotation data corresponding to the preset recording to obtain a trained preset neural network model; designing a recording text library for a user to select a target recording text for recording to obtain a currentrecording; performing secondary training on the trained preset neural network model by using the current recording and the target recording text; and extracting static voice parameters of to-be-synthesized text by using the preset neural network model subjected to secondary training, and inputting the static voice parameters into a synthesizer to obtain synthesized voice. According to the method,the problem that in the prior art, the quality and precision of the synthesized voice are low due to the facts that the data volume required by training is small, the quality is generally not high, the model prediction precisi