[ISEA2022] Artist Talk: Jonas Kraasch & Philippe Pasquier — Autolume: Automating Live Music Visualization

Artist Statement 

June 14, MACBA – Convent dels Àngels. Session: Sound, Data and AI

Keywords: Computer-assisted creativity, Deep Learning, Generative Adversarial Network, VJ, Music Visualisation, Video Generation, New media, Artificial Intelligence, Live Performance, Intelligent Systems

Deep Learning is becoming increasingly more accessible for artists, leading to generative and discriminative models being used for artistic expression. We distilled approaches found in research and installations relating to GANs into a live VJing program. We propose an interactive tool for visualizing music using live audio feature extraction and a MIDI controller to allow artists to accompany live performances. Following previous approaches for offline audio-reactive visuals using GANs, we map the amplitude, onset strength and notes in the music to influence the images generated. Furthermore, we use findings in interpretable GANs and techniques in Network Bending to incorporate a MIDI controller that is common for VJs. This allows the artist to adjust the visuals with a known interface.

  • Philippe Pasquier (FR/CA) is a professor at Simon Fraser University’s School for Interactive Arts and Technology, where he directs the Metacreation Lab for Creative AI. Philippe leads a research-creation program around generative systems for creative tasks. As such, he is a scientist specialized in artificial intelligence, a multidisciplinary media artist, an educator, and a community builder. His contributions range from theoretical research in and creative AI, multi-agent systems, computational creativity, machine learning, affective computing, evaluation methodologies, to applied artistic research and practice in digital art, computer music, as well as interactive and generative art.
  • Jonas Kraasch is a graduate student at Simon Fraser University’s School for Interactive Arts and Technology (Canada), where he is part of the Metacreation Lab for Creative AI. With his prior studies in Cognitive Science with a focus on Deep Learning his goal is to combine both his passions for AI and creative expression by creating both creative systems and tools to assist artists in their work. In his research he focuses on deep learning, machine learning, creative AI, data ethics and generative models