An Artist Conducts a Generative Orchestra of Bells

Budhaditya Chattopadhyay explores how technology can mediate a listener’s experience of sound in his latest project, Dhvāni.

By Google Arts & Culture

Budhaditya Chattopadhyay

Artist Budhaditya Chattopadhyay is known for exploring how technology can mediate a listener’s experience of sound through large-scale installation and live performance. 

Through attentive listening– and a collection of more than three terabytes of field recordings– Chattopadhyay transforms ephemeral experiences into sonic traces. 

His artworks have been exhibited, performed or presented in Transmediale, Berlin; ZKM Center for Art and Media, Karlsruhe; Donau Festival, Krems; Harvestworks, New York City; and Screen City Biennial, Stavanger, Norway, among others. 

Detail: Budhaditya Chattopadhyay (2020)

Here, Budhaditya talks through his latest project, Dhvāni, developed as part of the AMI grants residency.

Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

Budhaditya Chattopadhyay artist introduction
00:00

Budhaditya, introduce yourself.

Detail: Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

How would you describe your arts practice?

Sound is my primary medium.

I'm deeply interested in pre-modern sounds, or sounds that existed before the intervention of modernist recording technologies. Like temple bells or wind chimes.

I work with field recordings and found objects. And I always carry a sound recorder wherever I go. 

Budhaditya Chattoopadhyay (2020) by Mari-Leen Kiipli

Budhaditya Chattopadhyay on his artist studio in Tallinn, Estonia
00:00

Since 2005, I’ve recorded more than three terabytes of field recordings. Attentive listening leads me to compose sonic traces from ephemeral experiences. 

Rendering: Budhaditya Chattopadhyay, "Dhvāni" (2019) by Budhaditya Chattopadhyay

Budhaditya Chattopadhyay introduces Dhvāni
00:00

Can you describe the piece you’ve created?

Dhvāni is a responsive and self-regulating sound installation: a network of 51 interconnected bells.

Installation view: Budhaditya Chattopadhyay: Dhvāni, EXPERIMENTA Arts & Sciences Biennale 2020 (2020) by Mari-Leen Kiipli

In 'Dhvāni' the audience’s presence and interaction are the primary motivations for a chance composition to evolve through inter-subjectivity.

Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

How does this project relate to your practice?

In my work, I use creative coding, programming algorithms and generative systems to develop responsive compositions and sonic environments that address urgent issues, like the climate crisis, human intervention in the environment and ecology, migration, race, and decolonization.

I try to connect the disparate resonances across the borders and cultures through a practice committed to advocating for reciprocity and equality in contemporary societies.

Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

This idea of reciprocity motivates me to work towards generative compositions driven by AI, since machine learning renders a work open-ended, inter-subjective, self-aware, and responsive.

Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

Budhaditya Chattopadhyay on ML for Dhvāni
00:00

What part did machine learning play in the artwork?

For this project, I wanted to relocate  and re-listen to pre-modern sounds within our contemporary machine society and its automated environments. 

And I wanted to explore how machine learning might help me conduct an orchestra of such ritualistic sounds into an automated and self-regulating composition, thereby reconnecting them to the natural worlds from where they have been emerging.

Together with Google creative technologists Parag K. Mital and Holly Grimm, we explored ways to train a model on compositions using sequencing models. 

Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

We trained a sequence model on two corpora (datasets) of individual bells recorded in different environments.

Each dataset was played in a different installation environment, and consisted of 50 stereo recordings, ranging from one to three seconds in length. 

These recordings were accompanied by a 10-minute “composition” wave file, which served as a ground truth sequence of sound for Google creative technologists to test the trained algorithm and see if our trained model performed well.

Installation view: Budhaditya Chattopadhyay: Dhvāni, EXPERIMENTA Arts & Sciences Biennale 2020 (2020) by Budhaditya Chattopadhyay

An early iteration of Dhvāni installed at EXPERIMENTA Arts & Sciences Biennale 2020 in Grenoble, France. 

Budhaditya Chattopadhyay (2020) by Mari-Leen Kiipli

What excites you about working with machine learning?

The alien agency that lies between human and the machine – and opportunities for collaboration, dialog, and conversation between human and machines, contrasted with moments of chance, contingency, indeterminacy and chaos.

Installation view: Budhaditya Chattopadhyay: Dhvāni, EXPERIMENTA Arts & Sciences Biennale 2020 (2020) by Budhaditya Chattopadhyay

Forthcoming iterations of Dhvāni will be shown at Networks Festival at the University of Franche-Comté (Besançon, France) and at Rewire Festival in The Netherlands. 

Credits: Story

Photography by Mari-Leen Kiipli
Special thanks to Budhaditya Chattopadhyay and the project team: Subhadeep Biswas, Holly Grimm, Cyril Diagne, Tobias Lintl and Parag K. Mital. 

Credits: All media
The story featured may in some cases have been created by an independent third party and may not always represent the views of the institutions, listed below, who have supplied the content.
Google apps