{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:28:34Z","timestamp":1781713714188,"version":"3.54.5"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888942","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":12,"title":["Effective Pre-Training of Audio Transformers for Sound Event Detection"],"prefix":"10.1109","author":[{"given":"Florian","family":"Schmid","sequence":"first","affiliation":[{"name":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Morocutti","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Foscarin","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Schl\u00fcter","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Primus","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096787"},{"key":"ref5","article-title":"CMKD: cnn\/transformer-based cross-model knowledge distillation for audio classification","author":"Gong","year":"2022","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446348"},{"key":"ref7","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Chen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389636"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-29"},{"key":"ref10","article-title":"Masked autoencoders that listen","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Huang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3428908"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3352248"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"ref16","article-title":"Multi-iteration multi-stage fine-tuning of transformers for sound event detection with heterogeneous datasets","volume-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Schmid"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-242"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10192960"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1614"},{"key":"ref23","article-title":"FoleyCrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref24","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Allen-Zhu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref27","article-title":"DCASE 2024 task 4: Sound event detection with heterogeneous data and missing labels","volume-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Cornell"},{"key":"ref28","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref29","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Touvron"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096110"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1266"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-61"},{"key":"ref35","article-title":"Knowledge distillation from transformers for low-complexity acoustic scene classification","volume-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Schmid"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref39","article-title":"HEAR: holistic evaluation of audio representations","author":"Turian","year":"2021","journal-title":"NeurIPS Competitions and Demonstrations Track"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888942.pdf?arnumber=10888942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:05Z","timestamp":1774416305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888942","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}