Speech synthesis method and device, computer device and storage medium

Abstract

The invention relates to a speech synthesis method and device, a computer device and a storage medium. The method comprises the steps that a speech text to be synthesized is split to obtain a plurality of split speech texts; the split speech texts are classified to obtain a first speech text and a second speech text, wherein the first speech text is a speech text containing user information, and the second speech text is a speech text not containing the user information; first speech corresponding to the first speech text is acquired, and second speech corresponding to the second speech text is acquired, wherein speech parameters of the first speech correspond to speech parameters of the second speech; and the first speech and the second speech are spliced to obtain synthesized speech of the speech text to be synthesized. According to the method, the speech parameters of the first speech correspond to the speech parameters of the second speech, so that the tone, volume and tone of thespliced synthesized speech are kept unified, smooth splicing is realized, and the abrupt feeling of speech at splicing points is greatly reduced.

Description

technical field [0001] The present application relates to the technical field of speech synthesis, in particular to a speech synthesis method, device, computer equipment and storage medium. Background technique [0002] Intelligent Speech Interaction (Intelligent Speech Interaction), based on technologies such as speech recognition, speech synthesis, and natural language understanding, endows products with an intelligent human-computer interaction experience of "listening, speaking, and understanding you". In the intelligent voice interaction scenario, the traditional voice synthesis method realizes the voice recording by manually pre-recording and splicing. [0003] However, in the method of manual pre-recording, it is difficult to achieve consistency in emotion, intonation, volume, etc. through manual recording, and it is easy to cause the voice obtained by splicing to have a very obvious sense of abruptness at the splicing point. [0004] Therefore, the speech obtained b...

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a speech synthesis method, device, computer equipment and storage medium for the technical problems that the speech obtained by the above speech synthesis method is difficult to meet the needs in terms of emotion, intonation and volume.

Images