Voice synthesis method and device, storage medium and electronic equipment

Abstract

The invention relates to a voice synthesis method and device, a storage medium and electronic equipment, and the method comprises the steps: inputting lyric data and music score data into an information extraction model, so as to obtain text information corresponding to the lyric data and music theory information corresponding to the music score data; inputting the text information and the music theory information into a voice synthesis model to obtain first voice waveform data and second voice waveform data, the voice synthesis model being used for performing joint processing on the text information and the music theory information; and determining voice synthesis data corresponding to the lyric data and the music score data according to the first voice waveform data and the second voicewaveform data. Therefore, the clear singing data and the accompaniment data can be changed according to different user styles, the corresponding accompaniment data can be generated according to the music score created by the user, and the comprehensiveness of singing data synthesis is improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to a speech synthesis method, device, storage medium and electronic equipment. Background technique [0002] Nowadays, there are more and more applications and functions of song speech synthesis. However, in actual use scenarios, when performing song speech synthesis, it is usually used to extract some parts of existing songs as background sound templates, so that based on this background sound template for speech synthesis. However, the background sound template is strictly consistent with the corresponding music score information. Different users have different styles when performing speech synthesis, and it is difficult to ensure the matching of the background sound when performing speech synthesis under different user styles. [0003] At present, there is no good solution to solve the above problems. Contents of the invention [0004] This section is provided...

AI Technical Summary

Problems solved by technology

However, the background sound template is strictly consistent with its corresponding score information. When performing speech synthesis, different users have different styles, and it is difficult to ensure the matching of the background sound when performing speech synthesis under different user styles.

[0003] At present, there is no good solution to solve the above problems

Images