Eunsu Kang, Donald Craig, Austin Dill, Songwei Ge, Barnabas Poczos


Aural Fauna (2019) project presents an unknown form of organism,  aural fauna, that reacts to the visitor’s sound and touch. According to The Sirens of Titan, harmoniums feed on humming vibrations on the planet’s surface, the song of Mercury. They perceive the world through touch. Inspired by them, the  aural fauna is a family of creatures that become “alive” when there is a sound or touch fed into them. The fauna also sing in harmony to the visitor’s sound to express their acceptance of the visitor’s presence. The bodies and sounds of the fauna are generated through machine learning.  The creatures’ bodies appear as 3D-printed or virtual forms in the video projection. The unique form of each entity is designed by creative AI developed by the artist team. Their sound is generated in real-time using the WaveGAN algorithm in response to the participant’s touch. This project presents a utopian vision of the world where different species, and possibly even machines, interact with each other with no fear and without the rejection or hatred that spring from it; the human visitor and  aural fauna create harmony together.

This project is created by Eunsu Kang in collaboration with Donald Craig, Austin Dill, Songwei Ge, and Barnabas Poczos. Special thanks to Chun-Liang Li and Manzil Zaheer for their help in the algorithm development.

This project is using machine learning algorithms, ADD and PDD, that we have designed and developed for the 3d form generation. The interactive audiovisual system of this project is also developed by the artist team. The generated forms are  3D-printed by the artist. Sound generation is using WaveGAN implementation that is developed by Chris Donahue. We have modified it for our dataset that we have collected. Our sound dataset consists of various sounds including Poketmon sounds. 

This project has been selected for the ISEA 2019 exhibition in Gwangju, Korea. It is currently exhibited at the Sylvia Wald & Po Kim Art Gallery in NYC, USA. This project is one of the outcomes from our ongoing journey toward the creative AI.