Generative Spatial Synthesis of Sound and Music

ERC AdG

The ERC G3S project, designed by and for musicians and sound creators, will explore generative approaches to spatialization based on machine learning. As such, the project seeks to break away from the standards that shape the way we create and perceive spatiality, opening up to a diversity of spatial audio models, practices and generative processes.

Activities

Publications

Designing Interfaces for Spatial Musical Expression: An Ideation Workshop [Extended Abstract]

This workshop focuses on the design and lo-fi prototyping of novel interfaces for spatial musical expression. Participants will discuss what such interfaces might look, feel, and behave like, and consider which materials, gestures, and mappings could support intuitive and expressive control of spatial sound. Working with lo-fi prototyping materials provided by the organizers, participants will…

Read more

Exploring 2D Ambisonics by Amplitudes and Phases [Long paper]

This paper presents a spectral-like reformulation of two-dimensional ambisonics, enabling an alternative representation of the sound field in terms of amplitudes and phases. We situate this work within electroacoustic music creation, framing spatial audio as a synthesis problem. The amplitude-phase approach we propose allows for continuous manipulation and distortion of the sound field, starting from…

Read more

Opening Up Sound Spaces [Long paper]

The widespread availability of equipment and processes for creating sound spaces in the digital audio field has been accompanied by a musical and technical convergence towards certain ‘mainstream’ spatialization processes based on the acoustic modeling of point sources in a reverberant environment. But the question arises to understand how far this approach of sound spatialization…

Read more

Team

GithubInstagram