Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Video object sound effect searching and matching method, system and device and readable storage medium

A matching method and object technology, which is applied in the field of video processing, can solve the problems of slow accuracy, time-consuming, and low accuracy, and achieve the effect of high accuracy

Pending Publication Date: 2020-09-18
杭州星合尚世影视传媒有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing video processing technology, including video editing, special effects, subtitles or adding audio materials, etc., are all carried out independently. It is possible to let people speak first and record it directly in the video, but it is difficult to match the voices in the video except for the characters. Now, the sound part of the shooting scene is not completed by the foley artist, and then produced in post-production,

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
  • Video object sound effect searching and matching method, system and device and readable storage medium
  • Video object sound effect searching and matching method, system and device and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0052] Example 1:

[0053] A video object sound effect search matching method, such as figure 1 As shown, including the following steps:

[0054] S100. Obtain the category of a specific sounding object based on the video to be processed and construct the audio of the specific sounding object;

[0055] S200: Process the category of the specific sound-producing object in the video to be processed and the audio introduction of the audio to obtain a first matching score;

[0056] S300. Obtain the BERT vector of the object category of the specific sounding object and the BERT vector of the audio introduction, and then obtain the cosine similarity of the BERT vector, and use the cosine similarity as the neural network matching score;

[0057] S400: Obtain a video and audio matching score based on the first matching score and the neural network matching score;

[0058] S500. According to the audio matching scores, select several audios corresponding to the matching scores as the matching audios...

Example Embodiment

[0103] Embodiment 2: A video object sound effect search and matching system, such as figure 2 As shown, it includes an acquisition building module 100, a first processing module 200, a second processing module 300, a matching score acquisition module 400, and a selection matching module 500;

[0104] The acquisition and construction module 100 is configured to acquire the category of a specific sound-producing object and construct the audio of the specific sound-producing object based on the video to be processed;

[0105] The first processing module 200 is configured to process the category of the specific vocal object in the video to be processed and the audio introduction of the audio to obtain a first matching score;

[0106] The second processing module 300 is used to obtain the BERT vector of the object category of the specific sounding object and the BERT vector of the audio introduction, and then obtain the cosine similarity of the BERT vector, and use the cosine similarity a...

Example Embodiment

[0125] Example 3:

[0126] A computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0127] Obtain the category of a specific sounding object based on the video to be processed and construct the audio of the specific sounding object;

[0128] Process the category of the specific vocal object in the video to be processed and the audio introduction of the audio to obtain the first matching score;

[0129] Obtain the BERT vector of the object category of the specific sounding object and the BERT vector of the audio introduction, and then obtain the cosine similarity of the BERT vector, and use the cosine similarity as the neural network matching score;

[0130] Obtain video and audio matching scores based on the first matching score and the neural network matching score;

[0131] According to the audio matching scores, several audios corresponding...

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 a video object sound effect searching and matching method. The method comprises the steps: acquiring the category of a specific sound production object based on a to-be-processed video, constructing the audio of the specific sound production object, processing the category of the specific sounding object in the to-be-processed video and the audio introduction of the audio to obtain a first matching score, obtaining a BERT vector of the category of tghe specific sounding object and a BERT vector of audio introduction, further obtaining cosine similarity of the BERT vector, taking the cosine similarity as a neural network matching score, obtaining a video and audio matching score based on the first matching score and the neural network matching score, and selecting audios corresponding to the plurality of matching scores as matched audios of the specific sounding object according to the audio matching scores. Through video object sound effect searching and matching, special effect dubbing does not need to be carried out by means of a mimicry when video dubbing is carried out, the sound effect can be directly and automatically generated and matched to the corresponding video, convenience and rapidness are achieved, and the accuracy is high.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a video object sound effect search and matching method, system, device and readable storage medium. Background technique [0002] At present, with the development of science and technology, multimedia audio and video technology is widely used in various fields. Matching sound effects to specific sound objects in the video will give the audience a better feeling and help the audience to understand and understand various fields. Cognition, how to make a good-looking video is more important. [0003] In the existing video processing technology, including video editing, special effects, subtitles or adding audio materials, etc., are all carried out independently. It is possible to let people speak first and record it directly in the video, but it is difficult to match the voices in the video except for the characters. Now, the sound part of the shooting scene is not...

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
IPC IPC(8): G10L25/51G10L25/54G10L25/57G06K9/00G06N3/04G06N3/08
CPCG10L25/51G10L25/54G10L25/57G06N3/08G06V20/40G06N3/045Y02D10/00
Inventor 薛媛金若熙
Owner 杭州星合尚世影视传媒有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products