Audio synthesis method for audio electronic book, electronic device and computer storage medium

Abstract

The invention discloses an audio synthesis method for an audio electronic book, an electronic device and a computer storage medium. The method comprises determining a plurality of objects included inan electronic book text of the audio electronic book, and a plurality of original audio files corresponding to the audio electronic book; for each object, determining the original audio file corresponding to the object, and extracting at least one audio segment corresponding to the object from the original audio file corresponding to the object according to the position of the object in the electronic book text and a corresponding relationship between the electronic book text and the original audio file corresponding to the object; and synthesizing a synthesized audio file corresponding to theaudio electronic book according to the extracted at least one audio segment corresponding to each object. According to the method, a user can select different people to read the same book according to his or her preference during a process of listening to the electronic book, thereby improving user experience.

Description

technical field [0001] The invention relates to the field of computers, in particular to an audio synthesis method for an audio electronic book, electronic equipment and a computer storage medium. Background technique [0002] With the development of technology, more and more e-books are converted into audio e-books for readers to listen to. Through audio e-books, users can learn the content of the book directly without watching, so it is more intuitive, convenient and fast. Based on the above advantages, audio e-books are increasingly loved by readers. [0003] However, the inventor found that in the process of realizing the present invention, in the prior art, an audio e-book is usually recorded by a dubber, and a dubber can complete the dubbing of many audio e-books, so reading users can In the process of listening to an audio e-book, usually only one person's voice can be heard, so it is tedious, and the user cannot choose his favorite voice to read the audio e-book, re...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found that in the process of realizing the present invention, in the prior art, an audio e-book is usually recorded by a dubber, and a dubber can complete the dubbing of many audio e-books, so reading users can In the process of listening to an audio e-book, usually only one person’s voice can be heard, so it is relatively monotonous, and users cannot choose their favorite voice to read the audio e-book, resulting in poor user experience

Images