I’ve worked with Shimon on many deep learning and generative, interactive music systems. These have been used in numerous concerts and performances worldwide. The recent highlights featured here include an hour long performance with the Aarhus Jazz Orchestra which won the “Jazz Denmark Prize” (Danish Grammy’s) and a live broadcast in the Netherlands.
In September 2019 Shimon performed a 60 mintute work composed by Signe Bisgaard and Morten Riis. This involved Shimon acting as a travelling musician, playing precomposed music, improvising in jazz sections, reading graphic scores and responding to visual cues.
The concert was awarded the Jazz Denmark Prize (equivalent to the Grammy’s in the US) for “the most innovative and creative concert experience of the year”.
This performance had a huge amount of press, including TV, Radio and Newspaper Articles. Some highlights were:
In October 2017 Shimon recorded a live broadcast (with myself on Saxophone), in the Netherlands. The full broadcast can be seen below:
Mechatronics-Driven Musical Expressivity for Robotic Percussionists
New Interfaces for Musical Expression 2020
Ning Yang, Richard Savery, Raghavasimhan Sankaranarayanan, Lisa Zahray, Gil Weinberg
Abstract: Musical expressivity is an important aspect of musical per- formance for humans as well as robotic musicians. We present a novel mechatronics-driven implementation of Bru- shless Direct Current (BLDC) motors in a robotic marimba player, named Shimon, designed to improve speed, dynamic range (loudness), and ultimately perceived musical expres- sivity in comparison to state-of-the-art robotic percussionist actuators. In an objective test of dynamic range, we find that our implementation provides wider and more consistent dynamic range response in comparison with solenoid-based robotic percussionists. Our implementation also outper- forms both solenoid and human marimba players in striking speed. In a subjective listening test measuring musical ex- pressivity, our system performs significantly better than a solenoid-based system and is statistically indistinguishable from human performers.