Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization
Big data analysis and collation for data-driven head-related transfer function (HRTF) personalization methods are often hindered by systematic differences between HRTF datasets. To address this issue, we designed Task 1 of the inaugural listener acoustic personalisation (LAP) challenge. Researchers...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Signal Processing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11097362/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850043612098723840 |
|---|---|
| author | Rapolas Daugintis Roberto Barumerli Michele Geronazzo Johan Pauwels Lorenzo Picinali Katarina C. Poole |
| author_facet | Rapolas Daugintis Roberto Barumerli Michele Geronazzo Johan Pauwels Lorenzo Picinali Katarina C. Poole |
| author_sort | Rapolas Daugintis |
| collection | DOAJ |
| description | Big data analysis and collation for data-driven head-related transfer function (HRTF) personalization methods are often hindered by systematic differences between HRTF datasets. To address this issue, we designed Task 1 of the inaugural listener acoustic personalisation (LAP) challenge. Researchers were invited to propose strategies for harmonizing HRTFs from a collection of eight different datasets so that dataset-specific artifacts were mitigated while preserving the perceptually relevant attributes of the original HRTFs. Defining the two-sided task required a deeper assessment of the acoustic and perceptual HRTF descriptions to find an evaluation framework that encompassed the two domains. Consequently, a two-stage evaluation was devised to assess the submissions. First, an auditory sound localization model was used to test the perceptual validity of the harmonized HRTFs by estimating the difference in sound localization performance between the original and the harmonized versions. Then, a machine learning classifier was employed to differentiate harmonized HRTF datasets, and its accuracy was used to rank submissions. Three submissions were received, and one was declared a winner according to the evaluation criteria. Further analysis of the submissions revealed some limitations of the evaluation system, prompting a comprehensive review of the task’s inherent complexities. This paper serves as a systematic account of the challenge and relevant considerations, intended to guide future advancements in the field of HRTF personalization research. |
| format | Article |
| id | doaj-art-112e2304b5bd4fab858e05b01d291cce |
| institution | DOAJ |
| issn | 2644-1322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Signal Processing |
| spelling | doaj-art-112e2304b5bd4fab858e05b01d291cce2025-08-20T02:55:12ZengIEEEIEEE Open Journal of Signal Processing2644-13222025-01-01695096410.1109/OJSP.2025.359260111097362Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset HarmonizationRapolas Daugintis0https://orcid.org/0000-0001-9444-2448Roberto Barumerli1https://orcid.org/0000-0002-0155-3921Michele Geronazzo2https://orcid.org/0000-0002-0621-2704Johan Pauwels3https://orcid.org/0000-0002-5805-7144Lorenzo Picinali4https://orcid.org/0000-0001-9297-2613Katarina C. Poole5https://orcid.org/0000-0002-7101-7294Audio Experience Design, Dyson School of Design Engineering, Imperial College London, London, U.K.Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, ItalyAudio Experience Design, Dyson School of Design Engineering, Imperial College London, London, U.K.Centre for Digital Music, Queen Mary University of London, London, U.K.Audio Experience Design, Dyson School of Design Engineering, Imperial College London, London, U.K.Audio Experience Design, Dyson School of Design Engineering, Imperial College London, London, U.K.Big data analysis and collation for data-driven head-related transfer function (HRTF) personalization methods are often hindered by systematic differences between HRTF datasets. To address this issue, we designed Task 1 of the inaugural listener acoustic personalisation (LAP) challenge. Researchers were invited to propose strategies for harmonizing HRTFs from a collection of eight different datasets so that dataset-specific artifacts were mitigated while preserving the perceptually relevant attributes of the original HRTFs. Defining the two-sided task required a deeper assessment of the acoustic and perceptual HRTF descriptions to find an evaluation framework that encompassed the two domains. Consequently, a two-stage evaluation was devised to assess the submissions. First, an auditory sound localization model was used to test the perceptual validity of the harmonized HRTFs by estimating the difference in sound localization performance between the original and the harmonized versions. Then, a machine learning classifier was employed to differentiate harmonized HRTF datasets, and its accuracy was used to rank submissions. Three submissions were received, and one was declared a winner according to the evaluation criteria. Further analysis of the submissions revealed some limitations of the evaluation system, prompting a comprehensive review of the task’s inherent complexities. This paper serves as a systematic account of the challenge and relevant considerations, intended to guide future advancements in the field of HRTF personalization research.https://ieeexplore.ieee.org/document/11097362/Computational auditory modelinghead-related transfer function harmonizationHRTF datasetmachine learning classification |
| spellingShingle | Rapolas Daugintis Roberto Barumerli Michele Geronazzo Johan Pauwels Lorenzo Picinali Katarina C. Poole Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization IEEE Open Journal of Signal Processing Computational auditory modeling head-related transfer function harmonization HRTF dataset machine learning classification |
| title | Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization |
| title_full | Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization |
| title_fullStr | Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization |
| title_full_unstemmed | Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization |
| title_short | Listener Acoustic Personalization Challenge—LAP24: Head-Related Transfer Function Dataset Harmonization |
| title_sort | listener acoustic personalization challenge x2014 lap24 head related transfer function dataset harmonization |
| topic | Computational auditory modeling head-related transfer function harmonization HRTF dataset machine learning classification |
| url | https://ieeexplore.ieee.org/document/11097362/ |
| work_keys_str_mv | AT rapolasdaugintis listeneracousticpersonalizationchallengex2014lap24headrelatedtransferfunctiondatasetharmonization AT robertobarumerli listeneracousticpersonalizationchallengex2014lap24headrelatedtransferfunctiondatasetharmonization AT michelegeronazzo listeneracousticpersonalizationchallengex2014lap24headrelatedtransferfunctiondatasetharmonization AT johanpauwels listeneracousticpersonalizationchallengex2014lap24headrelatedtransferfunctiondatasetharmonization AT lorenzopicinali listeneracousticpersonalizationchallengex2014lap24headrelatedtransferfunctiondatasetharmonization AT katarinacpoole listeneracousticpersonalizationchallengex2014lap24headrelatedtransferfunctiondatasetharmonization |