An intelligent splitting method based on audio and video separation

An audio and video separation and intelligent technology, applied in the field of media asset management, can solve problems such as time-consuming and labor-intensive, user communication obstruction, etc., and achieve the effect of high efficiency and accuracy.

Active Publication Date: 2022-03-11
TENCENT TECH (SHENZHEN) CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional way of splitting long videos requires a lot of labor to manually preview and split videos, which is time-consuming and labor-intensive. It is impossible to deeply mine homogeneous and similar content in a short period of time and verify its repeatability, which affects accurate user communication. great hindrance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be further described below.

[0015] The technical scheme that this embodiment mode adopts is: it comprises the following steps:

[0016] 1. Separate the audio and video streams from the input video, and synchronize the audio and video streams according to the timestamp;

[0017] 2. Use object tracking technology to segment the scene of the video, and roughly separate the scene fragments;

[0018] 3. Perform speech recognition on the audio clips corresponding to each scene clip, and segment the scene clips according to the recognized text: for the scene clips that can recognize the text, separate the text paragraphs through the text classification method, and subdivide each scene clip according to the paragraphs ; For the scene segment that cannot recognize the text, perform step 4;

[0019] 4. According to the rhythm of the audio, voiceprint and other information, the scene segment is subdivided: for the scene segment where the text cannot ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent stripping method based on the separation of audio and video. The specific steps are: separating the audio and video streams from the input video; using object tracking technology to segment the scene of the video, and roughly separating the scene segments; Speech recognition is performed on the audio clips corresponding to each scene clip, and the scene clips are subdivided according to the recognized text; or the scene clips are subdivided according to the rhythm of the audio, voiceprint and other information; using deep learning technology, based on video understanding, the video clips are sorted label; finally, return the stripped video segment with the label; the method of the present invention effectively improves the efficiency and accuracy of video stripped.

Description

technical field [0001] The invention relates to the technical field of media asset management, in particular to an intelligent splitting method based on audio and video separation. Background technique [0002] Driven by the technology of mobile Internet, big data, and AI intelligence, short videos are breaking the traditional thinking of the content industry with their own advantages. With the development of 5G technology, the operating cost of the platform is reduced, the speed of the mobile terminal is greatly improved, the traffic of the short video blowout and the outstanding marketing effect are greatly improved, and the social activity and stickiness of users are greatly improved, which is more and more in line with the time of mobile users. Fragmented experience. But at the same time, how to accurately split long videos into multiple independent short videos based on content information of different natures has become an urgent problem to be solved. The traditional...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/8547H04N21/43H04N21/845H04N21/439H04N21/44H04N21/84
CPCH04N21/8547H04N21/4307H04N21/8456H04N21/4394H04N21/44008H04N21/84
Inventor 康洪文
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap