Cross-screen television content capturing method based on voiceprint recognition

A voiceprint recognition, TV content technology, applied in selective content distribution, electrical components, image communication, etc., can solve problems such as timely response to user interests and spiritual demands, and achieve the effect of high security

Inactive Publication Date: 2019-11-05
彩云之端文化传媒(北京)有限公司
View PDF13 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

After the above fragmented short videos are available for users to watch, but the above-mentioned public fragmentation method mainly depends on the views and angles of the fragmentation personnel, which is highly subjective, and there is a very strong intelligent fragmentation method. objectivity, and did not respond in a timely manner to the interests and spiritual appeals of the users themselves

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

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cross-screen television content capturing method based on voiceprint recognition
  • Cross-screen television content capturing method based on voiceprint recognition
  • Cross-screen television content capturing method based on voiceprint recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Embodiment 1 of the present invention provides a method for capturing TV content across screens based on voiceprint recognition. figure 1 As shown, the method includes the following steps:

[0029] S1: Steps of transcoding and storing into the library Cloud server with voiceprint SDK installed 1 Monitoring channel source satellite live channel source signal reception and collection 5 (live) or on-demand program upload 6 (on-demand)

[0030] The audio and video streams of the cloud server 1 TV media server 2 and voiceprint server 3 are stored in 7, and transcoded (converted to a stream that can be recognized by the network TV server and can be transmitted on the Internet) to form TV media data Library 4, to obtain transcoded audio and video streams into the library; the channel source includes audio and video streams from IPTV, digital TV or analog TV, the audio and video streams can also be transcoded (for example, the wireless signal from the satellite is converted into IPT...

Embodiment 2

[0042] Embodiment 2 is a method for capturing TV content across screens based on voiceprint recognition provided on the basis of Embodiment 1. The multiple-length recording segments include m-length recording segments of T duration, and the m-th segment is greater than the m-th segment. Duration of 1 recording segment, T m > T m-1 . When m=3, T1 is 3s, T2 is 5s, and T3 is 15s.

Embodiment 3

[0044] Embodiment 3 is a method for capturing TV content across screens based on voiceprint recognition provided on the basis of Embodiment 2, and the matching is sequential matching of m recording segments. That is, m1, m2, and m3 are matched in sequence until the match is successful. If it is still matched, it is necessary to obtain multiple time-length recording clips again for matching.

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 provides a cross-screen television content capturing method based on voiceprint recognition. The method comprises the following steps: S1, carrying out transcoding and warehousing; s2, performing audio separation; s3, extracting voiceprints and establishing a voiceprint library; s4, extracting a recording fragment voiceprint; s5, carrying out recording fragment voiceprint matching; s6, pushing an identification result; s7, intercepting a short video; and S8, editing and publishing the short video. The method breaks through the limitation of a transmission physical network, is unlimited in service application range, and can be applied to all television transmission fields of analog televisions, cable televisions, digital televisions, IPTVs and the like. The method can extractthe voiceprint in the video, but the voiceprint cannot be restored into the video, so that the data transmission has no leakage risk, and the security is high.

Description

Technical field [0001] The invention belongs to the field of television content interception, and particularly relates to a method for cross-screen television content interception based on voiceprint recognition. Background technique [0002] With the development of the economy, there are more and more multimedia organizations. These organizations can generate countless movies, TV series, documentaries, variety shows and other long video programs every day. Due to restrictions on copyright and other reasons, many wonderful content can only be watched by certain audiences in specific channels. For example, a popular drama first broadcasted on a live channel on the TV side, mobile terminal users cannot download, watch, forward, etc., and users watch The status of the content is static and single; and because there are more and more long video resources now, most users do not have enough time to watch the long video, they will watch the long video through fast forward and other mean...

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 Applications(China)
IPC IPC(8): H04N21/233H04N21/2343H04N21/235H04N21/258H04N21/431H04N21/435H04N21/439H04N21/4402H04N21/45H04N21/845H04N21/8547
CPCH04N21/2335H04N21/2343H04N21/25866H04N21/4312H04N21/435H04N21/235H04N21/4398H04N21/4402H04N21/4532H04N21/8456H04N21/8547
Inventor 刘晓初黄克叶小蕾张元王伟周为张战军
Owner 彩云之端文化传媒(北京)有限公司
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