Method for displaying multi-person conference in real time by combining audios and videos, medium and electronic equipment

Abstract

The invention provides a method for displaying a multi-person conference in real time by combining audios and videos, a medium and electronic equipment. The method comprises the following steps: acquiring audio data of speakers in conference participants; performing voice recognition processing on the audio data to obtain text information of the speaker; and synchronously displaying the text information in an area corresponding to the speaker in the conference video containing the speaker in real time, wherein the text information of each speaker is in one-to-one correspondence with the position of each speaker in the conference video. According to the invention, the speaker text information and the conference video are synchronously combined in real time, and the text information is displayed in the corresponding area of the speaker in the conference video, so that the speaking content of the speaker is easy to distinguish. Because the videos and the characters can be synchronously recorded, the recording forms are diversified and clear, and subsequent reading and understanding are facilitated.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method, medium and electronic equipment for real-time presentation of a multi-person conference combining audio and video. Background technique [0002] With the in-depth application of Internet technology, the popularity of various terminal devices is getting higher and higher. At present, there are many voice products that can support real-time transcription of conference speeches, and display the transcription content on the screen, which is convenient for other participants. Attendees read. However, the existing meeting transcription system also has some defects: when many people speak at the same time, it is often difficult to distinguish the identities of multiple speakers and their corresponding speech content, the content of the meeting minutes is chaotic, and the quality of the meeting minutes is low , and usually based on the manual recording of the pa...

AI Technical Summary

Problems solved by technology

However, the existing meeting transcription system also has some defects: when many people speak at the same time, it is often difficult to distinguish the identities of multiple speakers and their corresponding speech content, the content of the meeting minutes is chaotic, and the quality of the meeting minutes is low , and usually based on the manual recording of the participants, it is very easy to miss or record mistakes, and the efficiency is low; in addition, only text is used to display / record the content of the meeting, and the form of display / recording is relatively simple, and the content of the meeting minutes cannot be fully utilized

Images