Voice synthesis method, device and equipment and medium

Abstract

The embodiment of the invention discloses a voice synthesis method, device and equipment and a medium, and relates to a voice technology, a natural language processing technology and a deep learning technology. The voice synthesis method comprises the following steps: acquiring a target dialogue statement, determining a target character role involved in the target dialogue statement, based on thetarget dialogue statement, determining description information of the target character role, wherein the description information comprises at least one of a person label, a role relationship, a role identity and a dialogue scene, determining the character emotion of the target character by utilizing the target dialogue statement and the description information of the target character, and if the target dialogue statement meets the voice synthesis triggering condition, performing voice synthesis on the target dialogue statement according to the target character and the character emotion of thetarget character. According to the embodiment of the invention, the role substitution feeling and the picture feeling of voice broadcast can be improved.

Description

technical field [0001] The embodiment of the present application relates to computer technology, specifically to speech technology, natural language processing technology and deep learning technology, and in particular to a speech synthesis method, device, device and medium. Background technique [0002] The development of speech synthesis technology has not only brought great convenience to people's daily life, such as the widespread promotion of smart home appliances that support voice interaction, but also changed the way people read e-books. More and more e-book products support voice broadcast of text, and listening to books has become a new way for people to use their fragmented time to read books. [0003] However, at present, the voice broadcast of most e-books is relatively single, and the emotional expressiveness of the voice is insufficient, which cannot bring the audience a visual sense of the character picture, and cannot arouse the audience's sense of substitut...

AI Technical Summary

Problems solved by technology

[0003] However, at present, the voice broadcast of most e-books is relatively single, and the emotional expressiveness of the voice is insufficient, which cannot bring the audience a sense of the character picture visually, nor can the audience feel the role substitution.

Images