Chord Recognition in Beatles Songs

Chord Recognition in Beatles Songs

While a graduate student at MIT’s Media Lab, I collaborated with office-mate Vi­ctor Adán to explore how if we might train a machine to recognize chord changes in music. We tried multiple models to solve the problem, including Support Vector Machines, Neural Networks, Hidden Markov Models, and a few variations of Maximum Likelihood systems.

We chose Beatles tunes as a subset of the larger problem and trained our systems with 16 songs from three of their albums. Our systems processed 2700 training samples, 150 validation samples, and 246 testing samples. Our most successful system, a Support Vector Machine, achieved 68% accuracy in testing.

Our intention was to further the research which will lead to applications such as automatic transcription, live tracking for improvisation, and computer-assisted (synthetic) performers. Our models were an extension of the research provided by the following papers:

  • Musical Key Extraction from Audio, Steffen Pauws
  • Chord Segmentation and Recognition using EM-Trained Hidden Markov Models, Alexander Sheh and Daniel P.W. Ellis
  • SmartMusicKIOSK: Music Listening Station with Chorus-Search Function, Masataka Goto
  • A Chorus-Section Detecting Method for Musical Audio Signals, Masataka Goto

Main Website

Similar Posts

  • Contrapuntal Composer

    Contrapuntal Composer is Prolog code which writes music for three simultaneous voices. Depending on initial parameters, it can write a fugue, a rondo, or any other contrapuntal form. Contrapuntal Composer obeys the rules of good voice leading within each voice and between the voices.

  • SoundScratch

    SoundScratch is a set of extensions I wrote to manipulate audio in a children’s programming language called Scratch. The environment emphasizes the expressive capabilities of sound through the act of creation and design.

  • Be The Shortstop!

    Be The Shortstop! is a permanent public indoor installation at The Baseball Museum in Riverfront Stadium, Wichita KS. Players hit a large button on a kiosk to start the game. After a few seconds the game starts as they race to hit the correct button on a large wall. A crowd cheers on speakers as…

  • The Incubator

    The Incubator is an art piece which was initially installed as part of TechArtICT’s Dreamgrass installation at Exploration Place Fall 2022. Within the installation it was the machine where faceless children were created and indoctrinated. A Center TV displayed a teleprompter which offered encouragement for viewers to become participants, reading into a microphone placed at…

  • Touch #2

    Touch #2 is a playful virtual environment and an interactive, musical instrument. Viewers become participants through play. The piece installs on any flat wall with a high ceiling. Sensors mount on top of the wall to detect multitouch. A virtual environment of suns, stars and planets projects onto the wall. Gravity, inertia, friction, and wind…