Universite ofertas em França

Organisation/Company Université Paris 8 Department MUSI Research Field Computer science » Informatics Engineering » Sound engineering Researcher Profile First Stage Researcher (R1) Positions PhD Positions Country France Application Deadline 15 Oct 2025 - 17:00 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 35,3 Offer Starting Date 1 Jan 2026 Is the job funded through the EU Research Framework Programme? Horizon Europe - ERC Reference Number Project 101199875 — G3S Is the Job related to staff position within a Research Infrastructure? No

The position offered is a three-year funded PhD within the framework of the ERC Advanced Grant G3S project.

Presentation of the G3S project

Machine learning is particularly well suited to dealing with ill-defined problems, where complexity precludes direct solutions; it is therefore of vital importance in the field of music creation, where compositional knowledge is far from explicit. Until now, the generation of sound spaces has often been neglected in the application of AI to music and sound, whereas 3D spatial audio is the subject of major industrial developments and standardisation.

The ERC Advanced Grant project G3S (Generative Spatial Synthesis of Sound and Music), designed by and for musicians and sound creators, will explore generative approaches to spatial audio based on machine learning. In this way, it will tend to break away from the standards that shape the way we create or perceive spatiality, opening up to all the methods and processes of spatial audio. It is positioned in an original way at the rarely explored intersection of spatialisation and AI, the latter considered in a frugal, local and open source way, and within the framework of an international collaborative research and creation network.

From a large set of varied musical pieces proposing a construction of the sound space, from which we will collect the sound engines (represented by the operations on the signal), their multichannel recordings and the semantic descriptions of spatiality, we will train low-dimensional learning models, combining existing neural techniques. These models will be used to generate sound spaces and to explore them by means of user requests, either functional (describing the desired processing) or imitating an audio result, or semantic (describing the desired space). The spatial engines selected by the user can be exported in the form of plugins.

Over five years, the G3S project will implement and articulate four major research objectives: 1) the design of a unified operational representation of existing spatial audio engines 2) the proposal of a thesaurus and quantitative measures to describe the spatiality of sound 3) the generation of sound spaces from machine learning 4) the design of user interfaces to explore spatial audio. We will produce open source environments, compatible with audio standards and shared with the computer music community; we will validate them by commissioning composers, creating works, workshops and concerts.

Details of assignements

You will be integrated into the project team (3 postdoctoral researchers, 4 doctoral students) under the scientific supervision of PI Prof. Alain Bonardi; your thesis will be supervised by Alain Bonardi and co-supervised by André Villa, Senior Lecturer in the Music Department at Paris 8 University; your work will be closely monitored by Paul Goutmann, postdoctoral researcher.With a view to conducting high-level original research that will explore generative approaches to spatial audio based on machine learning, largely drawing on research-creation methods, your research will focus more specifically on research objective No. 2 above, namely the proposal of a thesaurus and quantitative measures for describing the spatiality of sound.

In particular, you will have to:

• Collect from member institutions of our international research network a corpus of recordings of multichannel musical and sound works, as well as the spatial audio intentions of the composers who created them. This data collection will be carried out in collaboration with another doctoral student involved in the project, who is responsible for research objective No. 1 (unified operational representation of spatial audio engines).
• Use this corpus to build a thesaurus, i.e., a structured directory of terms describing the spatial qualities of sound.
• Build a set of quantitative descriptors of sound spatiality, based on multichannel signals or external sound recordings.
• Highlight the relationships between the qualitative thesaurus and quantitative descriptors.
• Experiment with and evaluate your models in artistic creation situations (composer residencies) by offering validation through studio listening, within a research-creation framework.
• Contribute to a number of project deliverables: production of open source software components, production of high-level international publications.

The general duties of your position will consist of contributing to :

• research and research-creation conducted in the G3S project;
• exchanges with the international collaborative research and creation network;
• the production of project deliverables, including publications and communications;
• the organization and implementation of various forms of project dissemination (symposiums, study days, workshops, concerts, website, newsletter, etc.).

E-mail alain.bonardi@univ-paris8.fr

Research Field Computer science » Informatics Education Level Master Degree or equivalent

Research Field Engineering » Sound engineering Education Level Master Degree or equivalent

Skills/Qualifications

Knowledge

• You have completed a Master's degree in either music or computer science, with strong skills in computer music in both cases.
• You have experience in research-creation, in which technologies are considered not as ends in themselves but as levers opening up new ways of creating music and sounds, in the context of experimental music, in the studio and in concert.
• You have knowledge and experience of spatial audio and its processes.
• You have initial experience working in a team on collective research projects.
• advanced practice in Max and Pure Data environments;
• scientific rigor, open-mindedness, and commitment to the team are expected;
• good level of musical training; experience in musical and/or sound creation is desirable;
• knowledge of spatial audio principles and methods.

Research Field Computer science » InformaticsEngineering » Sound engineering Years of Research Experience 1 - 4

Selection process

To apply, please send a CV and covering letter (in French or English) to:

• Alain Bonardi, Professor of Computer Science and Musical Creation, Principal Investigator of the ERC Advanced Grant G3S Project (Generative Spatial Synthesis of Sound and Music), alain.bonardi@univ-paris8.fr