Multimedia transliteration method and system

Abstract

The invention provides a multimedia transliteration method is applied to a multimedia transliteration system and comprises the following steps of: S1, receiving a demonstration manuscript, and constructing a key information tree of the demonstration manuscript; S2, receiving voice data, carrying out voice identification on the voice data, and obtaining transliteration texts of the voice data; S3, synchronizing the voice data and the transliteration texts with the demonstration manuscript by means of the key information tree; and S4, displaying the demonstration manuscript with the synchronized voice data and transliteration texts to a user. The user can hear the voices of a speaker and see the texts transliterated by the voices of the speaker while seeing the demonstration manuscript, and furthermore, the transliteration texts are segmented according to sub-themes included in each page of the transliteration texts, the transliteration texts of the same sub-theme is in one segment, and the transliteration texts of different sub-theme serve as different segments, so that the user can conveniently understand the transliteration texts, and the experience of the user is further improved.

Description

technical field [0001] The invention relates to the field of voice signal processing, in particular to a multimedia transcription method and system. Background technique [0002] In recent years, with the rapid development of speech recognition technology, automatic speech recognition related products have been widely used in all walks of life. Converting speech into text greatly facilitates people's daily needs. For example, converting conference recordings into corresponding texts is convenient for meetings. The secretary will follow-up to query meeting information or assist him in writing meeting minutes; or convert interview recordings into corresponding texts, and edit drafts on this basis. However, the above-mentioned applications only convert the recording into text, and cannot simultaneously see the presentation corresponding to the voice data, especially when there is important information in the presentation, but the important information does not exist in the tran...

AI Technical Summary

Problems solved by technology

However, the above-mentioned applications only convert the recording into text, and cannot simultaneously see the presentation corresponding to the voice data, especially when there is important information in the presentation, but the important information does not exist in the transcription result, the user must follow the Voice data or transcribed text to find the corresponding presentation. If there are a lot of presentations, it is difficult to quickly find the presentation corresponding to the transcribed text, which reduces the user experience; for example, the recorded voice data is the teacher's classroom teaching recording , the teacher often gives various reference materials or their corresponding links in class, or demonstration operations when explaining knowledge points. These contents are often not found in the voice data or transcribed text data, and students must go to the transcribed text corresponding can only be viewed in the presentation of the

[0003] The existing transcription system generally directly transcribes the recorded voice data into text data and displays it to the user. When the user views the transcribed text, he cannot see the corresponding presentation. When some important information only exists in the presentation, such as The important link contained in the picture; users have to find the corresponding presentation by themselves according to the recorded voice data or the transcribed text, the user experience is poor, and at the same time it cannot be done. Yes, when there are many presentations, it is difficult to quickly find the presentation corresponding to the transcribed text

Images