{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:27:28Z","timestamp":1781018848997,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3748522.3779786","type":"proceedings-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:17:49Z","timestamp":1781014669000},"page":"1231-1233","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer"],"prefix":"10.1145","author":[{"given":"Petros","family":"Vavaroutsos","sequence":"first","affiliation":[{"name":"Orfium Research, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodoros","family":"Palamas","sequence":"additional","affiliation":[{"name":"Orfium Research, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pantelis","family":"Vikatos","sequence":"additional","affiliation":[{"name":"Orfium Ressearch, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Pablo Alonso-Jim\u00e9nez Pedro Ramoneda R Oguz Araz Andrea Poltronieri and Dmitry Bogdanov. 2025. OMAR-RQ: open music audio representation model trained with multi-feature masked token prediction. arXiv:2507.03482.","DOI":"10.1145\/3746027.3756871"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Zal\u00e1n Borsos et al. 2023. Audiolm: a language modeling approach to audio generation. IEEE\/ACM transactions on audio speech and language processing 31 2523\u20132533.","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 3915\u20133924","author":"Chiu Chung-Cheng","year":"2022","unstructured":"Chung-Cheng Chiu, James Qin, Yu Zhang, Jiahui Yu, and Yonghui Wu. 2022. Self-supervised learning with random-projection quantizer for speech recognition. In International Conference on Machine Learning. PMLR, 3915\u20133924."},{"key":"e_1_3_2_1_4_1","unstructured":"Micha\u00ebl Defferrard Kirell Benzi Pierre Vandergheynst and Xavier Bresson. 2016. Fma: a dataset for music analysis. arXiv preprint arXiv:1612.01840."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Anmol Gulati et al. 2020. Conformer: convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100.","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"e_1_3_2_1_6_1","volume-title":"Kushal Lakhotia","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing, 29, 3451\u20133460."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1037\/xge0000688"},{"key":"e_1_3_2_1_8_1","unstructured":"Yizhi Li et al. 2023. Mert: acoustic music understanding model with large-scale self-supervised training. arXiv preprint arXiv:2306.00107."},{"key":"e_1_3_2_1_9_1","unstructured":"Titouan Parcollet Rogier van Dalen Shucong Zhang and Sourav Bhattacharya. [n. d.] Summarymixing: a linear-complexity alternative to self-attention for speech recognition and understanding."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Machine Learning. PMLR, 17627\u201317643","author":"Peng Yifan","year":"2022","unstructured":"Yifan Peng, Siddharth Dalmia, Ian Lane, and Shinji Watanabe. 2022. Branch-former: parallel mlp-attention architectures to capture local and global context for speech recognition and understanding. In International Conference on Machine Learning. PMLR, 17627\u201317643."},{"key":"e_1_3_2_1_11_1","unstructured":"Jordi Pons Oriol Nieto Matthew Prockup Erik Schmidt Andreas Ehmann and Xavier Serra. 2017. End-to-end learning for music audio tagging at scale. arXiv preprint arXiv:1711.02520."},{"key":"e_1_3_2_1_12_1","unstructured":"Jordi Pons and Xavier Serra. 2019. Musicnn: pre-trained convolutional neural networks for music audio tagging. arXiv preprint arXiv:1909.06654."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP48289.2020.9145170"},{"key":"e_1_3_2_1_14_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448314"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Haina Zhu Yizhi Zhou Hangting Chen Jianwei Yu Ziyang Ma Rongzhi Gu Yi Luo Wei Tan and Xie Chen. 2025. Muq: self-supervised music representation learning with mel residual vector quantization. arXiv preprint arXiv:2501.01108.","DOI":"10.1109\/TASLPRO.2025.3602320"}],"event":{"name":"SAC '26: 41st ACM\/SIGAPP Symposium on Applied Computing","location":"Grand Hotel Palace Thessaloniki Greece","acronym":"SAC '26","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 41st ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748522.3779786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:36:32Z","timestamp":1781015792000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748522.3779786"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":17,"alternative-id":["10.1145\/3748522.3779786","10.1145\/3748522"],"URL":"https:\/\/doi.org\/10.1145\/3748522.3779786","relation":{},"subject":[],"published":{"date-parts":[[2026,3,23]]},"assertion":[{"value":"2026-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}