Workshop Description

In recent years, artificial intelligence has opened new possibilities for audio generation in music-making. From real-time audio synthesis and manipulation to diffusion models and transformer-based architectures, a range of generative tools is now available to musicians and composers. These tools have the potential to not only change how sounds are created but also how we conceptualize and engage with musical form, instrumentality, and authorship.

This workshop invites sound and music researchers and practitioners across Montréal and Québec to share and discuss the creative possibilities enabled by AI-based audio generation. The goal is to exchange and experience with these emerging technologies, highlighting their artistic potential, and support for the community to remain at the forefront of research and research-creation in this rapidly evolving field.

Registration

Registration for this workshop is now closed.

We invite you to share this event on Facebook.

Schedule

Click here to view a PDF version of the schedule including abstracts. 

Part 1: Presentations (A832)

09:30 — Welcome/Bienvenue – Dominic Thibault
09:45 — Generative Reverberation and the Future of 3D Music Production – Jack Kelly
10:15 — AI in 64Kb: can we do more with less? – Philippe Esling
10:45 — Coffee Break/Pause Café
11:00 — AI Collaborators in Scorch: Ethical and Creative Considerations for LLMs in Algorithmic Composition – Norah Lorway
11:30 — Neural Audio Synthesis for Low-Latency Interaction – Franco Caspe

12:15 — Lunch/Dîner

13:15 — Quigital: Performing Corporate Culture – Elliot Britton
13:45 — Adding Sound to Street Views: A Generative AI framework for Street-resolution Audio Generation – Feng Fei 
14:15 — Coffee Break/Pause Café

Part 2: Demos (A832 and A833)

14:30 (A832) — Latent Bending: Creative Misuse of Pre-Trained Generative Audio Models – David Piazza
14:30 (A833) — Realtime latent space synthesis – Charles Bicari
15:00 (A832) — TISSERV (Tool for interactive sound space exploration with reactive visuals by classification) – Josue Medina Rueda
15:00 (A833) — Formachron - A tactile grid-based polymetric, polytuplet, polyphasic sequencer – Adam Tindale
15:30 (A832) — Using Generative AI for Adaptive Learning in Music – Alberto Acquilino
15:30 (A833) — On Using IRCAMs RAVE with Acoustic Instruments – James Ford
16:00 (A832) — Latent Manipulation in Virtual Game Environments – Austin Tecks

Join us for a day of discussion, sonic experimentation, and exploration at the intersection of AI and musical creativity.