{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:21Z","timestamp":1764399081175,"version":"3.46.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249059","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"664-669","source":"Crossref","is-referenced-by-count":0,"title":["Segment Transformer: AI-Generated Music Detection via Music Structural Analysis"],"prefix":"10.1109","author":[{"given":"Yumin","family":"Kim","sequence":"first","affiliation":[{"name":"MIPPIA Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seonghyeon","family":"Go","sequence":"additional","affiliation":[{"name":"MIPPIA Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00765"},{"key":"ref2","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3649449"},{"key":"ref7","article-title":"Watching the generative ai hype bubble deflate","author":"Widder","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Audio deepfake detection: A survey","author":"Yi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref10","article-title":"Add 2023: The second audio deepfake detection challenge","author":"Yi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03766-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3342107"},{"key":"ref13","article-title":"Sonics: Synthetic or not-identifying counterfeit songs","author":"Rahman","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"On the effectiveness of speech self-supervised learning for music","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-847"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref17","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"Castellon","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096458"},{"journal-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","year":"2024","author":"Li","key":"ref19"},{"key":"ref20","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"},{"journal-title":"Map-music2vec: A simple and effective baseline for self-supervised music audio representation learning","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2022-14"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref24","first-page":"1298","article-title":"Data2vec: A general framework for selfsupervised learning in speech, vision and language","volume-title":"International conference on machine learning","author":"Baevski","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1178723.1178734"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11070242"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref30","article-title":"An image is worth 16 \\times 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01587"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR51284.2021.00076"},{"key":"ref35","first-page":"47704","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888461"},{"key":"ref38","article-title":"Mustango: Toward controllable text-to-music generation","author":"Melechovsky","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Beat this! accurate beat tracking without dbn postprocessing","author":"Foscarin","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249059.pdf?arnumber=11249059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:06Z","timestamp":1764399006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249059","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}