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

Motion-driven intelligent music generation method and system

A motion-driven, intelligent technology, applied in the direction of neural learning methods, biological neural network models, electrical components, etc., can solve the problems of difficult soundtrack production, high time and economic costs, and achieve reduction of soundtrack production costs, time costs and economic costs The effect of reduction and strong diversity

Active Publication Date: 2021-09-21
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems existing in the prior art, the present invention provides a motion-driven intelligent music generation method and system, utilizes the characteristics of computer quickness and economy, designs a deep neural network structure and trains it, Constructed a motion-driven intelligent music generation system, realized the intelligent processing of motion video and generated original audio data, and then synthesized the function of soundtrack, which solved the difficulty, time and economic cost of soundtrack production mentioned in the above-mentioned background technology high problem

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
  • Motion-driven intelligent music generation method and system
  • Motion-driven intelligent music generation method and system
  • Motion-driven intelligent music generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042]The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0043] see Figure 1-6 , the present invention provides a technical solution: a motion-driven intelligent music generation method, the method flow is as follows figure 1 shown, including the following steps:

[0044] Step 1: Build the dataset. First, download a large number of sports videos with soundtracks on video websites (mixed cuts with soundtracks, collections, etc.); secondly, write a python program to automatically and equal-length crop the downloaded...

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 motion-driven intelligent music generation method and system. The method comprises the steps of data set construction, video frame image initial feature extraction, video frame feature time sequence association, audio original data generation and network training and testing. According to the method, a deep neural network structure is designed and trained by utilizing the convenience and economy of a computer, intelligent processing of a sports video is realized, original audio data is generated, and then the incidental music is synthesized, so that the problems of high difficulty in making the incidental music and high time and economic cost in the prior art are solved; further, a motion-driven intelligent music generation function system is established, feature extraction can be accurately carried out on input video data, high-quality music is generated, matching of the music and a motion scene is achieved, the subjective score MOS of the generated music is larger than 3.5, rapid and batched generation of incidental music is carried out on videos of themes such as sports and the like, and the time cost and the economic cost of music production are reduced by more than one time.

Description

technical field [0001] The invention relates to the technical fields of computer vision and intelligent soundtracking, in particular to a motion-driven intelligent music generation method and system. Background technique [0002] Exercise is a variety of activities that human beings cultivate their physical fitness in the process of development. Since the beginning of the 21st century, with the continuous advancement of science and technology, people have begun to seek to integrate various elements into sports, such as: adding music to sports videos to give the audience a stronger audio-visual experience. Music is an important form of expression in the field of art, which embodies the human thinking mode and is a unified combination of regularity and creativity. On the one hand, the production of music is based on certain knowledge of music theory; on the other hand, music itself carries certain human emotions. [0003] The technology of using deep learning technology to a...

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): H04N21/439H04N21/44H04N21/81G06N3/04G06N3/08
CPCH04N21/44008H04N21/4394H04N21/44012H04N21/4398H04N21/8113H04N21/8166G06N3/084G06N3/044G06N3/045
Inventor 吴庆波施兆丰李宏亮孟凡满许林峰潘力立
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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