Automatic composition method and system

An automatic and genetic algorithm technology, applied in the direction of neural learning methods, genetic rules, biological neural network models, etc., can solve problems such as inability to generate music optimization, uneven music, etc.

Active Publication Date: 2021-10-01
NANCHANG HANGKONG UNIVERSITY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing composition methods based on evolutionary algorithms, etc., generate uneven music, and need to manually jud...

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
  • Automatic composition method and system
  • Automatic composition method and system
  • Automatic composition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] like figure 1 , 2 Shown in and 3, the present invention provides a kind of automatic composition method, described method comprises the steps:

[0058] Step 101, constructing a music data training set.

[0059] The music data training set described in step 101 is constructed, specifically including:

[0060] S1 obtains the original music data set.

[0061] S2 uses a genetic algorithm to process the original music data set to obtain a generated music data set.

[0062] S21: counting the probability of occurrence of each pitch in the original music data set;

[0063] S22: Count the number of occurrences of adjacent 2 consecutive pitch data and adjacent 3 consecutive pitch data in the original data set;

[0064] S23: Utilize the genetic algorithm to generate random music according to the probability of occurrence of each pitch, and use the pitch data of 2 consecutive adjacent pitch data and 3 consecutive pitch data of the random music that appear in the original music...

Embodiment 2

[0092] The process of automatic composition is as follows:

[0093] S2-1, first use the music data generation module to generate music data, including the processing of the original music data set and the use of genetic algorithm to generate the music data set, and make the two merge to obtain the final music data training set, wherein the original music data set Including 24 suona music data.

[0094] S2-2. Evaluate each piece of music in the music data training set through the music evaluation module, including selecting representative music according to the comprehensive score of n-gram evaluation and rule evaluation, and manually scoring.

[0095] S2-3. Use the data expansion module to expand the human-evaluated score so that its scale is the same as that of the music data training set.

[0096] S2-4. Use the data fusion module to perform weighted calculations on the normalized evaluation scores of the three evaluations. In this embodiment, 0.7, 0.2, and 0.1 are respectiv...

Embodiment 3

[0103] Such as Figure 4 As shown, the present invention also provides a kind of automatic composing system, and described system comprises:

[0104] Music data training set construction module 401, for constructing music data training set;

[0105] The building block of the music data training set specifically includes:

[0106] The original music data set acquisition sub-module is used to obtain the original music data set;

[0107] The music data generation sub-module is used to process the original music data set by using a genetic algorithm to obtain and generate a music data set; in the genetic algorithm, an initial parent is generated according to the statistical probability of each pitch in the original music data set. Random music in the generation population. The fitness function in the genetic algorithm is M=S R-2-gram +S R-3-gram -S rule-N ; among them, S R-2-gram is the number of times that two consecutive adjacent pitch data appear in the original music da...

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 an automatic composition method and system. The method comprises the following steps of constructing a music data training set; taking the music data in the music data training set as the input of an LSTM network model, taking the quality data of the music data as the output of the LSTM network model, and training the LSTM network model by using the music data training set to obtain a trained LSTM network model; and by taking maximization of output of the trained LSTM network model as an optimization target, performing music generation by adopting an optimization algorithm. According to the method, the LSTM network model and the optimization algorithm are combined to realize automatic evaluation and optimization of the generated music, the generated music is automatically optimized, and the optimized music is automatically generated.

Description

technical field [0001] The invention relates to the technical field of automatic composition, in particular to an automatic composition method and system. Background technique [0002] Music is an art that enriches people's lives and has become an integral part of social life today. The automatic composition technology is a computer-based composition system based on main technical means such as algorithms, rules or structural models. Automatic composition technology has become one of the hotspots in the research of artificial intelligence technology. [0003] Existing composition methods based on evolutionary algorithms, etc., generate uneven music, and need to manually judge and select the generated music, and cannot automatically optimize the generated music and automatically generate optimized music. Contents of the invention [0004] The purpose of the present invention is to provide an automatic composition method and system to automatically optimize the generated m...

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): G10H1/00G06N3/04G06N3/08G06N3/12G06K9/62
CPCG10H1/0025G06N3/049G06N3/08G06N3/126G10H2210/111G06N3/044G06F18/22
Inventor 陈昊罗刚黎明王铭勋黄敏徐一晨张聪炫
Owner NANCHANG HANGKONG UNIVERSITY
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