element14 Community
element14 Community
    Register Log In
  • Site
  • Search
  • Log In Register
  • Community Hub
    Community Hub
    • What's New on element14
    • Feedback and Support
    • Benefits of Membership
    • Personal Blogs
    • Members Area
    • Achievement Levels
  • Learn
    Learn
    • Ask an Expert
    • eBooks
    • element14 presents
    • Learning Center
    • Tech Spotlight
    • STEM Academy
    • Webinars, Training and Events
    • Learning Groups
  • Technologies
    Technologies
    • 3D Printing
    • FPGA
    • Industrial Automation
    • Internet of Things
    • Power & Energy
    • Sensors
    • Technology Groups
  • Challenges & Projects
    Challenges & Projects
    • Design Challenges
    • element14 presents Projects
    • Project14
    • Arduino Projects
    • Raspberry Pi Projects
    • Project Groups
  • Products
    Products
    • Arduino
    • Avnet Boards Community
    • Dev Tools
    • Manufacturers
    • Multicomp Pro
    • Product Groups
    • Raspberry Pi
    • RoadTests & Reviews
  • Store
    Store
    • Visit Your Store
    • Choose another store...
      • Europe
      •  Austria (German)
      •  Belgium (Dutch, French)
      •  Bulgaria (Bulgarian)
      •  Czech Republic (Czech)
      •  Denmark (Danish)
      •  Estonia (Estonian)
      •  Finland (Finnish)
      •  France (French)
      •  Germany (German)
      •  Hungary (Hungarian)
      •  Ireland
      •  Israel
      •  Italy (Italian)
      •  Latvia (Latvian)
      •  
      •  Lithuania (Lithuanian)
      •  Netherlands (Dutch)
      •  Norway (Norwegian)
      •  Poland (Polish)
      •  Portugal (Portuguese)
      •  Romania (Romanian)
      •  Russia (Russian)
      •  Slovakia (Slovak)
      •  Slovenia (Slovenian)
      •  Spain (Spanish)
      •  Sweden (Swedish)
      •  Switzerland(German, French)
      •  Turkey (Turkish)
      •  United Kingdom
      • Asia Pacific
      •  Australia
      •  China
      •  Hong Kong
      •  India
      •  Korea (Korean)
      •  Malaysia
      •  New Zealand
      •  Philippines
      •  Singapore
      •  Taiwan
      •  Thailand (Thai)
      • Americas
      •  Brazil (Portuguese)
      •  Canada
      •  Mexico (Spanish)
      •  United States
      Can't find the country/region you're looking for? Visit our export site or find a local distributor.
  • Translate
  • Profile
  • Settings
Sensors
  • Technologies
  • More
Sensors
Blog Google’s Brain2Music Reconstructs Music from Previously Listened Songs
  • Blog
  • Forum
  • Documents
  • Quiz
  • Events
  • Polls
  • Members
  • Mentions
  • Sub-Groups
  • Tags
  • More
  • Cancel
  • New
Sensors requires membership for participation - click to join
  • Share
  • More
  • Cancel
Group Actions
  • Group RSS
  • More
  • Cancel
Engagement
  • Author Author: Catwell
  • Date Created: 9 Aug 2023 5:53 PM Date Created
  • Views 472 views
  • Likes 5 likes
  • Comments 0 comments
  • research
  • hmi
  • human
  • google
  • cabeatwell
  • human_body
  • ai
  • sensor
  • innovation
Related
Recommended

Google’s Brain2Music Reconstructs Music from Previously Listened Songs

Catwell
Catwell
9 Aug 2023

image

Researchers created an AI model that produces short music clips based on what someone listened to. (Image Credit: Mohamed_hassan)

Google researchers have developed Brain2Music, an AI tool that generates short song snippets based on the music someone listened to during their fMRI brain scans. Five volunteers participated in this study, listening to 15-second music clips, and the team examined their fMRI data. Anyone interested in listening to these tunes can head over to Google’s page and see how closely they sound like the original song.

The team used parts of the brain imaging data and music clips to train an AI tool that looks for connections between the music features. This includes the genre, instruments, rhythm, mood, and the volunteers’ brain signals. The team categorized each mood as happy, exciting, tender, scary, or angry. Each individual had the AI program form links between their brain activity patterns and different musical features.

Once trained, the AI translated the unseen brain imaging data remnants into a snippet closely resembling musical aspects of the original songs. Afterward, the team input that data into MusicLM, another Google AI model designed to produce music via text, like “a calming violin melody backed by a distorted guitar riff.” The team discovered that the AI model achieved 60% agreement based on the mood of the reconstructed and original music. And the AI most accurately identified classical music versus other genres.

At the end of the day, the goal behind this project is to offer more insight into how the human brain processes music. So far, the team discovered that primary auditory cortex brain regions became active as the participants listened to the songs. Additionally, the lateral prefrontal cortex plays a crucial role in interpreting the song’s meaning. However, researchers need to look further into this with more research. Previous research showed that various prefrontal cortex regions shifted while a freestyle rapper improvised.

In the future, researchers could observe the brain’s ability to process different music moods or genres. The team’s goal is to determine if AI can recreate music that people think about in their minds.

Have a story tip? Message me at: http://twitter.com/Cabe_Atwell

  • Sign in to reply
element14 Community

element14 is the first online community specifically for engineers. Connect with your peers and get expert answers to your questions.

  • Members
  • Learn
  • Technologies
  • Challenges & Projects
  • Products
  • Store
  • About Us
  • Feedback & Support
  • FAQs
  • Terms of Use
  • Privacy Policy
  • Legal and Copyright Notices
  • Sitemap
  • Cookies

An Avnet Company © 2025 Premier Farnell Limited. All Rights Reserved.

Premier Farnell Ltd, registered in England and Wales (no 00876412), registered office: Farnell House, Forge Lane, Leeds LS12 2NE.

ICP 备案号 10220084.

Follow element14

  • X
  • Facebook
  • linkedin
  • YouTube