Celebrity Gig MagazineCelebrity Gig MagazineCelebrity Gig Magazine
  • Home
  • Celebrities
    • Nigerian Celebrity
    • Foreign Celebrity
  • Business/Tech
  • Articles/Lifestyle
  • Movies / TV Series
  • Music
    • Videos
Notification Show More
Font ResizerAa
Celebrity Gig MagazineCelebrity Gig MagazineCelebrity Gig Magazine
Font ResizerAa
  • Instagram
  • Facebook
  • Twitter
  • Youtube
Search
  • HOME
  • Celebrities
    • Foreign Celebrity
    • Nigerian Celebrity
  • Business/Tech
  • Articles/Lifestyle
  • Music
  • Movies / TV Series
    • BBNaija
  • Videos

Top Stories

Explore the latest updated news!
Me, Wizkid and Davido are the most dragged celebrites

Me, Wizkid and Davido are the most dragged celebrites

Warm metalworking turns brittle semiconductors into flexible, high-performance electronic films

Warm metalworking turns brittle semiconductors into flexible, high-performance electronic films

Concerns trail cozy moment between Davido and Chioma in a club

Concerns trail cozy moment between Davido and Chioma in a club

Stay Connected

Find us on socials
248.1kFollowersLike
61.1kFollowersFollow
165kSubscribersSubscribe
Made by ThemeRuby using the Foxiz theme. Powered by WordPress
Business/Tech

A new model for symbolic music generation using musical metadata

Celebrity Gig
Last updated: October 1, 2024 12:55 pm
By Celebrity Gig Add a Comment
Share
A new model for symbolic music generation using musical metadata
SHARE
Screenshot of the team’s system demo showing its user interface. Credit: Han et al.

Artificial intelligence (AI) has opened new interesting opportunities for the music industry, for instance, enabling the development of tools that can automatically generate musical compositions or specific instrument tracks. Yet most existing tools are designed to be used by musicians, composers and music producers, as opposed to non-expert users.

Researchers at LG AI Research recently developed a new interactive system that allows any user to easily translate their ideas into music. This system, outlined in a paper published on arXiv preprint server, combines a decoder-only autoregressive transformer trained on music datasets with an intuitive user interface.

“We introduce the demonstration of symbolic music generation, focusing on providing short musical motifs that serve as the central theme of the narrative,” Sangjun Han, Jiwon Ham and their colleagues wrote in their paper. “For the generation, we adopt an autoregressive model which takes musical metadata as inputs and generates 4 bars of multitrack MIDI sequences.”

The transformer-based model underpinning the team’s symbolic music generation system was trained on two musical datasets, namely the Lakh MIDI dataset and the MetaMIDI dataset. Collectively, these datasets contain over 400,000 MIDI (musical instrument digital interface) files, which are data files containing various information about musical tracks (e.g., the notes played, the duration of notes, the speed at which they are played).

READ ALSO:  Documentaries Nigerian music artists | Pulse Nigeria

To train their model, the team converted each MIDI file into a musical event representation (REMI) file. This specific format encodes MIDI data into tokens representing various music features (e.g., pitch and velocity). REMI files capture the dynamics of music in ways that are particularly favorable for training AI models for music generation.






“During training, we randomly drop tokens from the musical metadata to guarantee flexible control,” wrote the researchers. “It provides users with the freedom to select input types while maintaining generative performance, enabling greater flexibility in music composition.”

In addition to developing their transformer-based model for symbolic music generation, Han, Ham and their colleagues created a simple interface that would make it accessible to both expert and non-expert users. This interface currently consists of a sidebar and a central interactive panel.

READ ALSO:  How Ford is using AI, augmented-reality and 3D printing to improve quality

In the sidebar, users can specify aspects of the music they want the model to generate, such as what instruments should be playing and the song’s tempo. After the model generates a song, they can edit the track in the central panel, for instance, by removing/adding instruments or adjusting the time at which they will start playing music.

“We validate the effectiveness of the strategy through experiments in terms of model capacity, musical fidelity, diversity, and controllability,” wrote Han, Ham and their colleagues. “Additionally, we scale up the model and compare it with other music generation models through a subjective test. Our results indicate its superiority in both control and music quality.”

The researchers found their model performed significantly well and could reliably generate a maximum of 4 bars of music based on the user’s specifications. In their future studies, they could improve their system further by extending the duration of the musical tracks their model can create, broadening the specifications that users can give, and further enhancing the system’s user interface.

READ ALSO:  Framework moves beyond binary decisions to offer a more nuanced approach

“Our model, trained to generate 4 bars of music with global control, has limitations in extending music length and controlling bar-level local elements,” wrote the researchers. “However, our attempts hold significance in generating high-quality musical themes that can be used as loop.”

More information:
Sangjun Han et al, Flexible Control in Symbolic Music Generation via Musical Metadata, arXiv (2024). DOI: 10.48550/arxiv.2409.07467

Journal information:
arXiv


© 2024 Science X Network

Citation:
A new model for symbolic music generation using musical metadata (2024, October 1)
retrieved 1 October 2024
from

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.

Categories

Articles/Lifestyle BBNaija Business/Tech Foreign Celebrity Movies / TV Series Music News Nigerian Celebrity Videos
TAGGED:computer newsgenerationhi-tech newshitechInformation TechnologyInnovationInventionsmetadatamodelMusicMusicalsymbolic
Share This Article
Facebook Twitter Copy Link Print
Leave a comment Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Content Safety

HERO

celebritygig.com

Trustworthy

Approved by Sur.ly

2022

Categories

Articles/Lifestyle BBNaija Business/Tech Foreign Celebrity Movies / TV Series Music News Nigerian Celebrity Videos

Celebrity Gig Magazine

CelebrityGig Magazine is a 21st century entertainment platform with credible and trusted, local and foreign entertainment news, exclusive celebrity gists and gossips on the go.

We support free press and freedom of speech. We are here to get contents to more audience.

Related Stories

Uncover the stories that are related to the post!
Converting gas-powered cars to EVs is a booming business
Business/Tech

Converting gas-powered cars to EVs is a booming business

Who Nigeria and Ghana’s fraudsters are, how they operate, and why they do it
Business/Tech

Who Nigeria and Ghana’s fraudsters are, how they operate, and why they do it

AWS launches Bedrock generative AI service, Titan LLMs
Business/Tech

AWS launches Bedrock generative AI service, Titan LLMs

Nigeria’s debt risky, unsustainable –Report
Business/Tech

Nigeria’s debt risky, unsustainable –Report

Coinbase warned by SEC of potential securities charges
Business/Tech

Coinbase warned by SEC of potential securities charges

Metal fatigue in anodes identified as key cause of solid-state lithium battery degradation
Business/Tech

Metal fatigue in anodes identified as key cause of solid-state lithium battery degradation

FG orders DisCo to disconnect uncertified transformers – Punch Newspapers
Business/Tech

FG orders DisCo to disconnect uncertified transformers – Punch Newspapers

Ogun will explore oil in Olokola 2023 – Abiodun
Business/Tech

Ogun will explore oil in Olokola 2023 – Abiodun

Show More
Celebrity Gig Magazine

CelebrityGig Magazine is a 21st century entertainment platform with credible and trusted, local and foreign entertainment news, exclusive celebrity gists and gossips on the go.

We support free press and freedom of speech. We are here to get contents to more audience.

  • Categories:
  • Home
  • Music
  • NG Celebs
  • FRGN Celebs

About Us

  • About Us
  • Credit
  • Contact Us

Quick Links

  • Instagram
  • Facebook
  • Twitter
  • Youtube

Designed by SEPTIN911 using the CelebrityGig 2.0

adbanner
AdBlock Detected
Our site is an advertising supported site. Please whitelist to support our site.
Okay, I'll Whitelist
Welcome Back!

Sign in to your account

Lost your password?