Speech synthesis method, device, equipment and medium

Abstract

The present disclosure provides a speech synthesis method, device, device, and medium, wherein the method includes: acquiring semantic features, phoneme features, and acoustic features of a target text; performing a first alignment operation on semantic features and acoustic features to obtain a first alignment result ; Perform a second alignment operation on the phoneme features and acoustic features to obtain a second alignment result; perform feature fusion according to the first alignment result and the second alignment result to obtain fusion features; generate a synthetic speech corresponding to the target text based on the fusion features. The present disclosure can better improve the speech synthesis effect.

Description

Technical field [0001] The present disclosure relates to the field of artificial intelligence, in particular, it relates to a speech synthesis method, apparatus, devices and media. Background technique [0002] With the development of artificial intelligence, such as online customer service, online education, voice assistant, intelligent audio, audio novels and other real-world scenarios it is widely used in voice synthesis technology, which can automatically convert text to speech (synthesized audio) . However, the conventional speech synthesis technology poor obtained results voice, i.e., speech synthesis poor effect. Inventive content [0003] In order to solve the above problems, or at least partly solve the above problems, the present disclosure provides a speech synthesizing method, apparatus, devices and media. [0004] According to an aspect of the present disclosure, there is provided a speech synthesis method, comprising: obtaining a target text semantic features, and ...

AI Technical Summary

Problems solved by technology

However, the speech effect obtained by the existing speech synthesis technology is not good, that is, the speech synthesis effect is poor

Images