System and method for synchronizing human voice signal with its written explanatory data

Abstract

The invention discloses a system and a method for synchronizing a human voice signal and text description data of the human voice signal. Through technical means of analyzing the human voice signal in an audio signal, obtaining starting time of voice segments in the human voice signal, corresponding words in the text description data corresponding to the audio signal to the voice segments in sequence and adjusting the display time of the words to be the starting time of the corresponding voice segments, the efficiency of adjusting the display time of the words can be improved and a technical effect of automatically adjusting the display time of the words to be the time when generating a corresponding human voice is achieved.

Description

technical field [0001] The present invention relates to a system and method for displaying time synchronization of words and sentences, in particular to a system and method for synchronizing human voice signals and text explanatory materials. Background technique [0002] The technical solution of the dynamic lyrics can enable the lyrics corresponding to the song file to be read when the song file is played, and the lyrics represented by the played human voice to be displayed synchronously. In fact, dynamic lyrics are not limited to use in song documents, any multimedia document containing human voices can use dynamic lyrics to simultaneously display the words and sentences expressed by human voices. [0003] As more and more multimedia playback software or multimedia players support dynamic lyrics, owners of multimedia files gradually hope that when multimedia playback software or multimedia players play audio signals in multimedia files, they can simultaneously display the...

AI Technical Summary

Problems solved by technology

However, these tool software only provide the user with manually modifying the display time of each word and sentence one by one, or increase or decrease the display time of all words and sentences as a whole

[0006] Since there are still some audio signals corresponding to the text description materials only record the words and sentences of the audio signal, but do not record the display time. In addition, some audio signals may have multiple versions. There may be a slight difference in time, for example, some human voices may be played earlier / later than the displayed time of the words and sentences. If you want to manually add or modify the display time of each word and sentence, it will take a lot of time and is very inefficient

[0007] In summary, it can be seen that there has been a problem in the prior art for a long time that it is impossible to efficiently adjust the display time of each word and sentence corresponding to the audio signal, so it is necessary to propose improved technical means to solve this problem

Images