{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:33:09Z","timestamp":1781584389626,"version":"3.54.5"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890881","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Pre-training with Synthetic Patterns for Audio"],"prefix":"10.1109","author":[{"given":"Yuchi","family":"Ishikawa","sequence":"first","affiliation":[{"name":"Keio University,LY Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshimitsu","family":"Aoki","sequence":"additional","affiliation":[{"name":"Keio University,Kanagawa,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref5","first-page":"28 708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.42"},{"key":"ref13","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"},{"key":"ref14","article-title":"Contrastive learning from synthetic audio doppelgangers","author":"Cherep","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01555-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01782"},{"key":"ref17","first-page":"2556","article-title":"Learning to see by looking at noise","volume":"34","author":"Baradad Jurjo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"6450","article-title":"Procedural image programs for representation learning","volume":"35","author":"Baradad","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_3"},{"key":"ref20","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref24","first-page":"438","article-title":"Openmic-2018: An open dataset for multiple instrument recognition","volume-title":"ISMIR","author":"Humphrey"},{"key":"ref25","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref26","first-page":"125","article-title":"Hear: Holistic evaluation of audio representations","volume-title":"NeurIPS 2021 Competitions and Demonstrations Track","author":"Turian","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625960"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1037\/emo0001048"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref32","first-page":"148","article-title":"Vocal imitation set: a dataset of vocally imitated sound events using the audioset ontology","volume-title":"DCASE","author":"Kim"},{"key":"ref33","article-title":"Libricount, a dataset for speaker count estimation","author":"St\u00f6ter","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02055"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"}],"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\/10890881.pdf?arnumber=10890881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:45Z","timestamp":1774416225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890881\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890881","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}