Listener Acoustic Personalisation (LAP) Challenge
A benchmarking campaign on acoustic and non-acoustic factors in immersive technologies.
Personalized Head-Related Transfer Functions (HRTFs) have shown promise in enhancing auditory localization and immersion in mixed realities. However, relevant issues such as the accurate acquisition of user-specific anatomical data, efficient simulation algorithms, and effective user validation do not converge into a common and internationally recognized benchmark for evaluating HRTFs.
The LAP Challenge endeavours to provide a platform where researchers can explore these challenges, advance the state of the art, and contribute to the development of standardized metrics for personalised spatial audio.
The inaugural edition of the challenge will concentrate on two fundamental aspects of HRTF: spatial sampling and interpolation. Teams are challenged to submit their solutions that address one of two tasks:
- Task 1: HRTF normalisation for merging different HRTF datasets
- Task 2: spatial upsampling for obtaining a high-spatial-resolution HRTF from a very low number of directions
Task description documents
The documents below outline the complete description for each task.
The evaluation code is also publicly available here:
Key Dates
- Task specifics released: March 27, 2024
- Evaluation code released: April 4, 2024
- Submission deadline: June 25, 2024
- Award ceremony: August 29, 2024
Workshop
The challenge will have an award ceremony hosted by the premier European conference on signal processing: the 32nd European Signal Processing Conference, EUSIPCO 2024, to be held in Lyon, France, on August 29th, 2024. The results will be presented in a 2-hour workshop.
The tentative program includes:
- Introduction to the LAP challenge and its roadmap.
- Announcement of final results and full rankings of the 1st edition.
- Invited talks from the winners of Task 1 and Task 2.
- Award ceremony to honour the achievements.
- Next steps toward the 2nd LAP challenge
Editorial aspects
Top-ranked solutions will be invited to submit a paper describing their method and result to be published in the IEEE Open Journal of Signal Processing (OJ-SP), a fully open-access publication of the IEEE Signal Processing Society, with a scope encompassing the full range of technical activities of the Society. Article processing charge (APC) waivers will be also available upon request.
Since the challenge provides original data and evaluation processes, participants also have the flexibility to submit already published solutions.
Awards
Winners of the two tasks will be invited to participate and reimbursed for the registration fee to EUSIPCO24 and, until available funds are reached, for travel and accommodation.
Organisers
Chair: Michele Geronazzo, University of Padova, IT, and Imperial College London, UK
Co-chair: Lorenzo Picinali, Imperial College London, UK
Chair of the Implementation: Roberto Barumerli, University of Verona, IT,
Chair of the Web Site and Dissemination: Aidan Hogg, Queen Mary University of London, UK
Fabian Brinkmann, Technische Universität Berlin, DE
Glen McLachlan, University of Antwerp, BE
Stavros Ntalampiras, University of Milan, IT
Johan Pauwels, Queen Mary University of London, UK
Katarina Poole, Imperial College London, UK
Rapolas Daugintis, Imperial College London, UK
The Listener Acoustic Personalisation Challenge is sponsored by the IEEE Signal Processing Society.
