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

Music infringement detection method

A detection method and music technology, applied in the field of data processing, can solve the problem that the accuracy and performance of infringement detection cannot be guaranteed, and achieve the effect of improving the accuracy and efficiency

Active Publication Date: 2021-02-26
杭州音度人工智能有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although the above patents can determine music infringement, they cannot guarantee the accuracy and performance of infringement detection

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
  • Music infringement detection method
  • Music infringement detection method
  • Music infringement detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0055] As an embodiment of the present invention, as an embodiment of the present invention, the convolutional neural network includes six convolutional layers and three fully connected layers, the convolutional layer contains eight 1x1 convolution kernels, and the fully connected layer Two layers in contain 1024 neurons, and one layer contains 2 neurons.

[0056] As an embodiment of the present invention, such as image 3 As shown, the specific process of filtering in step 4 is:

[0057] 4.1. Input the extreme point;

[0058] 4.2. Through the fully connected neural network;

[0059] 4.3. Whether the output retains the extreme point;

[0060] 4.4. Concatenate the remaining extremum points and output.

[0061] As an embodiment of the present invention, the fully connected neural network includes three layers, wherein both the first layer and the second layer contain 1024 neurons, and the third layer contains 2 neurons.

[0062]The present invention also provides a computer...

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 relates to a music infringement detection method. The method comprises the following steps: S1, performing short-time Fourier transform on each piece of music in a music library in sequence to obtain a frequency spectrum signal corresponding to each music ID; S2, performing dynamic resolution compression on the frequency spectrum signals; S3, for the compressed frequency spectrum signals, calculating an extreme point of each frequency band interval; S4, filtering the extreme points, and obtaining music vectors of the music library through pairwise subtraction of the extreme points; S5, compressing the music vectors of the music library into int32 bit by bit; S6, constructing a hash table by taking int32 as a Key and music ID as Value, and progressively increasing the music IDaccording to the time sequence of the music entering the music library to mark each piece of music; S7, inputting a training audio to obtain an infringement probability; and S8, inputting a test audio to obtain an infringement probability. According to the method, the spectrum information of the music is subjected to feature extraction through the convolutional neural network and the full-connection network, useful features can be extracted in multiple dimensions, manual screening is not needed, and the detection accuracy and efficiency are improved.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a music infringement detection method. Background technique [0002] The current popularization of the Internet has also brought about the widespread popularity of music. People can easily listen to and use music in various ways to create videos. But music is copyrighted. If copyrighted music is used in commercial videos at will, it will cause infringement and damage the rights and interests of music creators. [0003] The patent publication number CN101493918A discloses a music infringement method, specifically: [0004] The present invention relates to an online music piracy monitoring method and system, comprising the following steps in turn: an audio fingerprint extraction module obtains an audio download address from the Internet: an audio fingerprint extraction module reads an audio file from the audio download address, and obtains an audio file after p...

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): G10L15/02G10L15/16G06F21/12
CPCG10L15/02G10L15/16G06F21/12
Inventor 方煌锖俞挺张德华黄静惠柯登峰
Owner 杭州音度人工智能有限公司
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