Neural Audio Plugin Competition

Winners

• 

  1st Place

  Courtesy of

  

  

  

  • $2000 - courtesy of TikTok
  • JUCE indie or Max & RNBO license for each member (up to 4)
  • NAMM Ticket and Presenting opportunity (GPU Audio)
  

  Scyclone

  Github repo Watch video

  Fares SchulzChristian ScheerAmirpasha Mobini TehraniValentin Ackva

  While our plugin and trained models ensured data safety and compliance with copyright legislations to a maximum level, there is always the concern of culturally appropriating the source musicians especially with the Djemble dataset that originates from an African background and utilised in a centro-European context.

• 

  2nd Place

  Courtesy of

  

  

  

  

  • $1000 - courtesy of TAP & Qosmo
  • JUCE indie or Max & RNBO license for each member (up to 4)
  

  Neural Resonator

  Github repo Watch video

  Rodrigo DiazLewis WolstanholmeAdan Benito

  Physical simulations are used to train the model, and we are confident that it will not have any adverse impact on users nor raise any copyright or legal concerns.

• 

  3rd Place

  Courtesy of

  

  • $500 - courtesy of GPU Audio
  

  HARD

  Github repo Watch video

  Yiming Wu

  The neural network was trained using the music audio database maintained by AlphaTheta. Care has been taken to ensure that the training data is not biased toward any particular musical genre. Since the neural network model is intended to reconstruct the musical elements of the input audio, the risk of copyright violation due to the plug-in is very low.