{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T06:56:42Z","timestamp":1725692202012},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10289774","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T17:55:44Z","timestamp":1698861344000},"page":"391-395","source":"Crossref","is-referenced-by-count":0,"title":["On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers"],"prefix":"10.23919","author":[{"given":"Paul","family":"Primus","sequence":"first","affiliation":[{"name":"Institute of Computational Perception (CP-JKU)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[{"name":"Institute of Computational Perception (CP-JKU)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Masked spectrogram prediction for self-supervised audio pre-training","author":"chong","year":"2022","journal-title":"abs\/2204 12768"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"9th Int Conf on Learning Representations ICLR"},{"key":"ref14","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","author":"niizumi","year":"2022","journal-title":"abs\/2204 12260"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref11","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"CoRR vol abs\/1607 06450"},{"key":"ref22","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"6th International Conference on Learning Representations ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-61"},{"journal-title":"Gunshots recorded in an open field using ipod touch devices","year":"2020","author":"cooper","key":"ref21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref1","article-title":"AST: audio spectrogram trans-former","author":"gong","year":"2021","journal-title":"Annual Conference of the International Speech Communication Association INTERSPEECH"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd Inter Conf for Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref18","article-title":"HEAR: holistic evaluation of audio representations","author":"turian","year":"2021","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track NeurIPS"},{"key":"ref8","article-title":"Two at once: Enhancing learning and generalization capacities via ibn-net","author":"pan","year":"0","journal-title":"European Conference on Computer Vision ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00343"},{"key":"ref9","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"CoRR vol abs\/1607 08022"},{"key":"ref4","article-title":"A multi -device dataset for urban acoustic scene classification","author":"mesaros","year":"2018","journal-title":"Proc of the Detection and Classification of Acoustic Scenes and Events Workshop DCASE"},{"key":"ref3","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"chen","year":"2022","journal-title":"CoRR vol abs\/2212 09058"},{"key":"ref6","article-title":"Batch-instance normalization for adaptively style-invariant neural networks","author":"nam","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31 Annual Conf on Neural Information Processing Systems NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2023,9,4]]},"location":"Helsinki, Finland","end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10289774.pdf?arnumber=10289774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T19:08:18Z","timestamp":1702321698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10289774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10289774","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}