MIDI playing style automatic conversion system based on recurrent neural network

A technology of cyclic neural network and automatic conversion, which is applied to instruments, electro-acoustic musical instruments, etc., can solve problems such as lack of dynamics, and achieve the effect of speeding up training

Active Publication Date: 2020-08-18
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, intelligent composition mainly focuses on the constituent notes that produce music, namely pitch and duration, and lacks dynamics

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
  • MIDI playing style automatic conversion system based on recurrent neural network
  • MIDI playing style automatic conversion system based on recurrent neural network
  • MIDI playing style automatic conversion system based on recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] This embodiment discloses a MIDI performance style automatic conversion system based on a cyclic neural network. The system includes a sequentially connected MIDI analysis module, a data preprocessing module, an autoencoder module, a style network module and a music generation module. Among them, the MIDI analysis module is used to read the MIDI input by the user, and merge the multi-track MIDI into a single-track MIDI, and save the MIDI after merging the note tracks as a score; the data preprocessing module is used to extract the notes from the score feature to represent the score; the self-encoder module is used to encode and decode the extracted note features, to compress the surface features of the score and to extract the advanced features of the score; the style network module is used to learn the performance style of the score and generate a score that conforms to a specific performance style. The velocity vector of , assisting composition; the music generation mo...

Embodiment 2

[0084] Further illustrate the MIDI performance style automatic conversion system based on the cyclic neural network disclosed by the present embodiment below in conjunction with the accompanying drawings, as figure 1 Shown is a schematic diagram of the structure of the MIDI performance style automatic conversion system based on the cyclic neural network. The system includes MIDI analysis module, data preprocessing module, autoencoder module, style network module and music generation module. Among them, the MIDI analysis module is used to read the MIDI input by the user, and merge the multi-track MIDI into a single-track MIDI as a score; the data preprocessing module extracts the note features from the score, and designs the note matrix and velocity matrix to represent the score ;The autoencoder module is responsible for encoding and decoding the note matrix and the velocity matrix, which is used to compress the surface features of the score and extract the advanced features of...

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 an MIDI playing style automatic conversion system based on a recurrent neural network. The MIDI playing style automatic conversion system comprises an MIDI analysis module, a data preprocessing module, an auto-encoder module, a style network module and a music generation module. The MIDI analysis module is used for reading user input and combining the multi-track MIDI intoa single-track MIDI to serve as a music score; the data preprocessing module is used for extracting note features from the music score; the auto-encoder module encodes and decodes the note features; the style network module learns the playing style of the music score and predicts a strength vector; and the music generation module is used for configuring the strength vector predicted by the style network module for the music score and converting the strength vector into a music rich in expressive force. The automatic playing style conversion system disclosed by the invention meets personalizedrequirements of music enthusiasts and generates music of a playing style loved by a user; and meanwhile, the MIDI playing style automatic conversion system can be used as a tool for professionals, sothat the professionals can easily integrate new styles and creativity into composition work.

Description

technical field [0001] The invention relates to the technical field of computer-aided composition, in particular to a MIDI performance style automatic conversion system based on a cyclic neural network. Background technique [0002] In today's society, people are actively exploring a rich spiritual and emotional world while pursuing material living standards. As an effective way for people to express their emotions, music constitutes and supports the spiritual life of human beings, and plays an indispensable role in entertainment, education, and medical treatment. Different genres of music convey different musical styles. Grasping the style of music is of great significance for understanding music works. Whether a performer can really understand a musical work can only be judged by whether he has a correct grasp of the musical style during the performance process. Playing style can be described in terms of rhythm, strength, and timbre. [0003] Musical Instrument Digital...

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): G10H1/00
CPCG10H1/0025G10H2210/105G10H2210/131G10H2210/111G10H2210/145G10H2210/031G10H2250/005G10H2240/056G10H2250/311
Inventor 丁泉龙戴安东曹燕韦岗
Owner SOUTH CHINA UNIV OF TECH
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