Speech synthesis method, apparatus, device and storage medium

Abstract

The present invention provides a speech synthesis method, device, equipment and storage medium, by acquiring text information, and determining the characters in the text information and the text content of each of the characters; role identification, determining the role attribute information of each of the roles; according to the role attribute information of each of the roles, obtaining a speaker corresponding to each of the roles one by one, wherein the speaker is pre-stored with the The pronunciation object of the role attribute information; according to the text information and the speaker corresponding to the role of the text information, a multi-role synthesized voice is generated, which improves the pronunciation diversity of different roles in the synthesized voice, and improves the audience's understanding of the synthesis. The distinction between different roles in the voice improves the user experience.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of unmanned vehicles, and in particular to a speech synthesis method, device, equipment and storage medium. Background technique [0002] With the development of speech technology, speech technology has begun to be applied to all aspects of people's life and work. For example, in scenarios such as audio reading, man-machine dialogue, smart speakers, and smart customer service, the device can emit synthesized voice to serve users. [0003] In the prior art, the text to be processed can be acquired, and then the text is processed by using speech synthesis technology to obtain the speech. [0004] However, in the prior art, only a single speaker can be obtained through speech synthesis technology, but for a multi-role scene, the synthesized speech of multiple characters cannot be obtained. For example, when performing audio reading, it is necessary to obtain dialogue voices of multiple c...

AI Technical Summary

Problems solved by technology

[0004] However, in the prior art, only a single speaker can be obtained through speech synthesis technology, but for multi-role scenes, it is impossible to obtain multi-role synthesized speech

For example, when performing audio reading, it is necessary to obtain the dialogue voices of multiple characters, but in the prior art, the voice of a single speaker can only be obtained by performing speech synthesis on the text

Images