LINZ, Austria & HAMAMATSU, Japan–(BUSINESS WIRE)–Yamaha Corporation unveiled the world’s first*1 Artificial Intelligence (AI) piano system capable of playing any piece of music in the style of late legendary pianist Glenn Gould on September 7 at the Ars Electronica Festival, one of the world’s largest media arts festivals, held in Linz, Austria. The AI system also gave a concert performance at the festival, and Yamaha has now announced the release of video footage from the performance. The project has been recognized as one of several efforts celebrating 150 Years of Japanese-Austrian relations.
Check out the concert video at https://youtu.be/wmn0vKs_2dM
Please also check out the technology information at the project official website below.
The AI system consists of a player piano and the AI software, which instantly generates playing data that incorporates the unique touch, pacing, and other stylistic traits of Glenn Gould and then provides that data to the player piano. The system is distinguished by its world-first*1 application of deep learning technology*2 to play any piece of music in the style of Glenn Gould as long as sheet music data is available, and it does so almost impeccably via the use of AI technology, which has been rapidly evolving in recent years.
The system also includes Yamaha’s original AI Music Ensemble Technology that enables the system to analyze the performance of fellow human players near-instantly and play predictively while interacting with human musicians. More than simply an automated performance, the system reproduces the masterful touch of Glenn Gould to provide an inspiring and interactive experience of co-creation between an AI pianist and human musicians.
The concert was held at St. Florian Monastery on September 7, the third day of the Ars Electronica festival. In addition to a piano solo, the AI system performed a piano duet with Francesco Tristano and a wind trio with members of the Bruckner Orchestra Linz (violin and flute) for a performance “with contemporary artists that transcended space and time.”
After the performance, the audience members, who had filled the hall to capacity, erupted into applause. The concert was one of the top highlights of the event’s main program, “AI x Music Festival.”
Glenn Gould was also known for his devotion to recording with digital media and an interest in rethinking the relationship between performer and audience. The project name “Dear Glenn” is a tribute to the artist’s attitude, which helped reveal the possibilities of new technologies and was also the inspiration for the idea behind the project. Yamaha is confident that, through this project, it has taken steps toward presenting new possibilities in musical expression via co-creation and mutual inspiration between human musicians and modern AI technology.
Comments by Dear Glenn Project Participants and Members
“To bring artificial intelligence into connection with music should not end as an objective in a competition or an exhibition of achievements of two different forms of intelligence, but should be the beginning of a discussion which searches for forms of application in order to improve us in our being human and to expand and improve our virtuoso actions. ‘Dear Glenn,’ in its many different and wonderful manifestations, has proved to be a congenial example in this context and has more than met Ars Electronica’s high-quality standards.”
Martin Honzik, Senior Director, FESTIVAL/PRIX/EXPORT, Ars Electronica
“It was a pleasure to work with you all on this great research project, which is such a fitting tribute to the spirit and legacy of Glenn Gould. I am suggesting that this project be taken into the musical mainstream, where I know it will command keen interest and generate a great deal of attention as well as spirited debate.”
Brian M. Levine, Executive Director, Glenn Gould Foundation
“The lines between music, people, machines, and algorithms are dissolving, and ‘we are all part of it.’ I want to express my deepest gratitude to Yamaha for trusting in me and allowing me to contribute to the first AI that will provide an interpretation of one of the most visionary musicians in the history of the piano: Glenn Gould. This project means everything to me.”
Francesco Tristano, Pianist/Composer
“I would like to first offer my sincere thanks to everyone who believed in and supported this project. The evolution of information technology in the 20th century has provided us not only with a hardware revolution of the piano, but with a software revolution as well, including AI technology. We believe this AI will lead to an expansion of the boundaries of musical creativity from the standpoint of human sensitivity and this is a large part of what drives our research activities. By sharing some of our ongoing results with music enthusiasts at Ars Electronica, I feel we have taken another step toward realizing these new possibilities.”
Koichi Morita, Senior General Manager of Research & Development Division, Yamaha Corporation
Born in Toronto, Canada in 1932, Glenn Gould was a legendary pianist who passed away in 1982 at the young age of 50. In 1964, Gould announced the end of his concert career and began to concentrate on recording, devoting himself to digital media releases. Gould was also known for his unconventional and unique performance habits, which included sitting on a low chair and leaning over the piano keyboard, as well as humming while playing, even during recordings.
Since its founding in 1887, the Yamaha Corporation (HQ: Hamamatsu, Japan) has developed its business activities focusing on musical instruments, audio products, Yamaha music schools, semiconductors, and other products and services related to sound and music. With its unique expertise and sensibilities, gained from our devotion to sound and music, Yamaha is committed to creating excitement and cultural inspiration together with people around the world.
*1: As of August 2019, Yamaha Corporation’s internal survey.
*2: Deep learning is a machine learning method, and is characterized by the multilayered use of mathematical models called neural networks to process information.