{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:22:58Z","timestamp":1783610578054,"version":"3.55.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204339","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["AudioMAE++: Learning Better Masked Audio Representations with Swiglu FFNS"],"prefix":"10.1109","author":[{"given":"Sarthak","family":"Yadav","sequence":"first","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergios","family":"Theodoridis","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref3","article-title":"BEit: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao"},{"key":"ref4","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"International conference on machine learning","author":"Baevski"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume":"35","author":"Feichtenhofer","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230477"},{"key":"ref15","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","volume-title":"HEAR: Holistic Evaluation of Audio Representations","author":"Niizumi","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref17","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Masked autoencoders with multi-window local-global attention are better audio learners","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yadav"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-246"},{"key":"ref20","article-title":"Glu variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.816"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref23","article-title":"Understanding and improving transformer from a multi-particle dynamic system point of view","volume-title":"ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-588"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref27","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International conference on machine learning","author":"Dauphin"},{"key":"ref28","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1274"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref33","first-page":"5178","article-title":"Beats: audio pre-training with acoustic tokenizers","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Chen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Istanbul, Turkiye","start":{"date-parts":[[2025,8,31]]},"end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204339.pdf?arnumber=11204339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:32Z","timestamp":1762367852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204339","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}