GANs and Poses: An interactive generative music installation controlled by dance moves

R. Vogl, H. Eghbal-zadeh, G. Widmer, P. Knees. GANs and Poses: An interactive generative music installation controlled by dance moves. pages http://ismir2018.ircam.fr/pages/events-exhibition.html,, 9, 2018.

Autoren
  • Richard Vogl
  • Hamid Eghbal-zadeh
  • Gerhard Widmer
  • Peter Knees
BuchProceedings of ISMIR2018 Interactive Machine-Learning for Music (IML4M) @Exhibition
TypIn Konferenzband
Monat9
Jahr2018
Seitenhttp://ismir2018.ircam.fr/pages/events-exhibition.html,
Abstract

GANs and Poses is an interactive multi-media installation using human poses to control artificial neural networks generating parts for a music arrangement. To provide incentive for interaction, a game-style UI rewards the audience with audio-visual feedback, which in turn drives the progress through the musical arrangement. This work uses a variety of artificial neural networks to (i) detect persons and their body posture, (ii) classify dance moves, and (iii) generate drum as well as melody patterns.