machine learning

Computers that Learn to Listen

Institute of Computational Perception, Johannes Kepler University (JKU) Linz (AT)

A set of 8 short demo videos on latest results from the world of scientific research: computers learn to listen to and “understand” music; an autonomous drum robot recognizes beat and rhythm; musical computer companions turn music pages for pianists, listen to orchestras, provide synchronized scores to concert audiences, and accompany soloists.

Voices from AI in Experimental Improvisation

Tomomi Adachi (JP), Andreas Dzialocha (DE), Marcello Lussana (IT)

Through machine learning, computers can recognize patterns in a variety of sound documents. But can they also learn to improvise musically? The software “Tomomibot” tries it out by interacting in real time with the sound artist Tomomi Adachi, using deep learning techniques. The Artificial Intelligence (AI) "learns" the artist’s individual style via voice recordings and directly confronts him with the newly generated material. Their joint performance shows how interactive technology and AI can influence a (vocal) style. However, this dialogue also makes clear that the artist will always be more creative and unpredictable than his mechanical counterpart.

Reeps One x Dadabots ft. Second Self AI

Reeps One (UK)

Second Self is an art and science collaboration between Reeps One, Dada Bots and the E.A.T. program at Nokia Bell Labs. The collaboration is a live performance piece designed to integrate machine learning, the human voice, and generative audio as a practical artistic tool and to raise awareness about machine learning beyond the academic, technological and engineering demographics via the medium of film and performance.