Conference document information acquisition method and device and related equipment thereof

Abstract

The invention discloses a conference document information acquisition method. The method comprises the steps of collecting conference video information and conference audio information; performing feature extraction on the conference video information to obtain corresponding lip language features and text features; performing feature extraction on the conference audio information to obtain corresponding audio features; performing feature fusion on the lip language features, the text features and the audio features to obtain fusion features; processing the fusion features to obtain conference document information. According to the conference document information acquisition method, the comprehensiveness and accuracy of conference recording can be improved while the conference recording efficiency is ensured. The invention furthermore discloses a conference document information acquisition device and equipment, and a computer readable storage medium, which all have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of multimedia technology, in particular to a method for obtaining conference document information, and also relates to a conference document information obtaining device, device, and computer-readable storage medium. Background technique [0002] In video conferencing, it is particularly important to organize the video, audio, PPT and other information in the meeting effectively and with high quality to form complete written records. Traditional conference transcription methods mainly include manual recording through pen and paper and automatic recording based on speech recognition technology. [0003] The method of manual recording by pen and paper is extremely inefficient; the automatic recording method based on speech recognition technology only obtains the transcription document in a single voice mode, without other information in the meeting scene, such as the supplement of PPT information, etc. There ...

AI Technical Summary

Problems solved by technology

[0003] The method of manual recording by pen and paper is extremely inefficient; the automatic recording method based on speech recognition technology only obtains the transcription document in a single voice mode, without other information in the meeting scene, such as the supplement of PPT information, etc. There is also the problem of incomplete information recording, and when the voice environment is relatively noisy, the accuracy of voice recognition will drop significantly, resulting in inaccurate meeting records

Images