Sound reproduction method and device, readable medium and electronic equipment

Abstract

The invention relates to a sound reproduction method and device, a readable medium and electronic equipment. The method comprises the steps: acquiring a to-be-reproduced sound input by a user and a target template, wherein the to-be-reproduced sound is a sound segment, with any length, pronounced by the user; extracting to-be-reproduced frequency spectrum data from the to-be-reproduced sound; determining template text information corresponding to the target template; and determining target frequency spectrum data corresponding to the target template and the tone in the to-be-reproduced sound according to the to-be-reproduced frequency spectrum data and the template text information. Thus, the sound of the user can be reproduced according to the sound segment with any length input by the user, accordingly the text is vocalized through the sound of the user, and then text reading or song singing can be realized, sound input by the user according to limited contents is not needed, also the user does not need to carry out long-time sound input, and the sound reproduction complexity of the user is simplified on the premise of ensuring the sound reproduction effect.

Description

technical field [0001] The present disclosure relates to the technical field of speech synthesis, and in particular, to a sound reproduction method, device, readable medium and electronic equipment. Background technique [0002] In the prior art, if you want to copy the timbre of the speaker so as to automatically generate any speech with the timbre of the speaker, you need to obtain a sufficient amount of voice information from the speaker, or even require the speaker to input a large amount of specific voice Information can achieve a better sound reproduction effect, and the relevant sound reproduction model trained on the speech training data of a single speaker cannot be used by other people, so it is difficult to apply it in practical applications. Contents of the invention [0003] This Summary is provided to introduce a simplified form of concepts that are described in detail later in the Detailed Description. This summary of the invention is not intended to identi...

AI Technical Summary

Problems solved by technology

[0002] In the prior art, if you want to copy the timbre of the speaker so as to automatically generate any speech with the timbre of the speaker, you need to obtain a sufficient amount of voice information from the speaker, or even require the speaker to input a large amount of specific voice Information can achieve a better sound reproduction effect, and the relevant sound reproduction model trained on the speech training data of a single speaker cannot be used by other people, so it is difficult to apply it in practical applications

Images