The Creative Audio Synthesis and Interfaces Workshop was held at Queen Mary University of London on July 15th, 2025. This one-day workshop included a series of talks exploring the intersection of creative audio synthesis and AI-enabled synthesizer programming. Topics included evolutionary algorithms for sound exploration, synthesizer sound matching, timbre transfer, timbre-based control, reinforcement learning, differentiable digital signal processing, representation learning, and human-machine co-creativity.
Earlier this year, the AIM CDT visited the RITMO Centre for Interdisciplinary Studies in Rhythm, Time, and Motion at the University of Oslo in Norway. A shared interest in creative applications of audio synthesis and novel interface designs was established during this visit, motivating this follow-up workhshop at QMUL. Researchers from RITMO, The Open University, and the AIM CDT at QMUL were invited to share their work, engage in critical discussion, and map directions for future work. See below for a summary of talks with links to presentation recordings.
An evening concert showcased musical applications of technical implementations discussed during the workshop, grounding these discussions in real-world artistic contexts.
The Creative Audio Synthesis and Interfaces Workshop was organised by COMMA Lab members Jordie Shier, Haokun Tian, and Charalampos Saitis, and was supported by the UKRI Centre for Doctoral Training in Artificial Intelligence and Music (AIM) at the Centre for Digital Music (C4DM).
Invited Talks
Designing Percussive Timbre Remappings: Negotiating Audio Representations and Evolving Parameter Spaces
- Jordie Shier -- Queen Mary University of London
- Presentation Recording
Facilitating serendipitous sound discoveries with simulations of open-ended evolution
- Björn Thor Jónsson -- University of Oslo
- Presentation Recording
Autonomous control of synthesis parameters with listening-based reinforcement learning
- Vincenzo Madaghiele -- University of Oslo
- Presentation Recording
Can a Sound Matching Model Produce Audio Embeddings that Align with Timbre Similarity Rated by Humans?
- Haokun Tian -- Queen Mary University of London
- Presentation Recording
GuitarFlow: Realistic Electric Guitar Synthesis From Tablatures via Flow Matching and Style Transfer
- Jackson Loth -- Queen Mary University of London
Timbre latent space transformations for interactive musical systems oriented to timbral music-making
- Andrea Bolzoni -- The Open University
- Presentation Recording
Why Synthesizer Parameter Estimation Is Hard and How to Make it Easy
- Ben Hayes -- Queen Mary University of London
- Presentation Recording
Perceptually Aligned Deep Image Sonification
- Balint Laczko -- University of Oslo
- Presentation Recording
Modulation Discovery with Differentiable Digital Signal Processing
- Christopher Mitcheltree -- Queen Mary University of London
- Presentation Recording
Musical Performances and Demos
Experience Replay (Performance)
- Vincenzo Madaghiele -- University of Oslo
Weaving (Performance)
- Balint Laczko -- University of Oslo
Phylogeny (Demo)
- Björn Thor Jónsson -- University of Oslo