{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:10:53Z","timestamp":1778789453384,"version":"3.51.4"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"DFG","award":["442218748"],"award-info":[{"award-number":["442218748"]}]},{"name":"DFG","award":["AUDI0NOMOUS"],"award-info":[{"award-number":["AUDI0NOMOUS"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3688974","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:51:43Z","timestamp":1777492303000},"page":"67756-67764","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Sample Difficulty in Computer Audition Analysis"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8842-2958","authenticated-orcid":false,"given":"Manuel","family":"Milling","sequence":"first","affiliation":[{"name":"Chair of Health Informatics (CHI), Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8338-617X","authenticated-orcid":false,"given":"Andreas","family":"Triantafyllopoulos","sequence":"additional","affiliation":[{"name":"Chair of Health Informatics (CHI), Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9395-6367","authenticated-orcid":false,"given":"Simon","family":"Rampp","sequence":"additional","affiliation":[{"name":"Chair of Health Informatics (CHI), Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alican","family":"Akman","sequence":"additional","affiliation":[{"name":"Group on Language, Audio, and Music (GLAM), Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Chair of Health Informatics (CHI), Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s005300050106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.886615"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e23142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2023.1196079"},{"key":"ref5","article-title":"UniAudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023","journal-title":"arXiv:2310.00704"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3135152"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2019.18058"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-69920-0"},{"key":"ref9","article-title":"Sparks of large audio models: A survey and outlook","author":"Latif","year":"2023","journal-title":"arXiv:2308.12792"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2025.e41656"},{"key":"ref11","first-page":"70","article-title":"Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations","volume-title":"Proc. 6th Detection Classification Acoustic Scenes Events Workshop (DCASE)","author":"Triantafyllopoulos"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446177"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-977"},{"key":"ref14","article-title":"Trivial or impossible - dichotomous data difficulty masks model differences (on ImageNet and beyond)","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Meding"},{"key":"ref15","first-page":"10876","article-title":"Deep learning through the lens of example difficulty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baldock"},{"key":"ref16","article-title":"When do curricula work?","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref17","article-title":"Does the definition of difficulty matter? Scoring functions and their role for curriculum learning","author":"Rampp","year":"2024","journal-title":"arXiv:2411.00973"},{"key":"ref18","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv:1804.03209"},{"key":"ref19","first-page":"56","article-title":"Acoustic scene classification in DCASE 2020 challenge: Generalization across devices and low complexity solutions","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop (DCASE)","author":"Heittola"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref22","first-page":"5034","article-title":"Characterizing structural regularities of labeled data in overparameterized models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref24","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref27","article-title":"Autrainer: A modular and extensible deep learning toolkit for computer audition tasks","author":"Rampp","year":"2024","journal-title":"arXiv:2412.11943"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11499367.pdf?arnumber=11499367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:00:08Z","timestamp":1778788808000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11499367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3688974","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}