{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:23:50Z","timestamp":1778052230622,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"institute of information communications technology planning evaluation","award":["IITP-2026-RS-2022-00156389"],"award-info":[{"award-number":["IITP-2026-RS-2022-00156389"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3689044","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:51:43Z","timestamp":1777492303000},"page":"65618-65632","source":"Crossref","is-referenced-by-count":0,"title":["Discrete Audio Tokens as a Data-Efficient Representation for Acoustic Traffic Monitoring"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8464-2898","authenticated-orcid":false,"given":"Minhan","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8220-192X","authenticated-orcid":false,"given":"Seokjin","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"5","key":"ref1","first-page":"629","article-title":"A survey on intelligent transportation systems","volume":"15","author":"Qureshi","year":"2013","journal-title":"Middle-East J. Scientific Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3476475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco54536.2021.9615925"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447868"},{"key":"ref5","first-page":"216","article-title":"Pyroadacoustics: A road acoustics simulator based on variable length delay lines","volume-title":"Proc. 25th Int. Conf. Digital Audio Effects","author":"Damiano"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1205"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889208"},{"key":"ref8","article-title":"Jless submission to dcase2024 task10: An acoustic-based traffic monitoring solution","author":"Zhang","year":"2024"},{"key":"ref9","article-title":"Fine-grained audio feature representation with pretrained model and graph attention for traffic flow monitoring","author":"Fan","year":"2024"},{"key":"ref10","article-title":"DynamicSound simulator for simulating moving sources and microphone arrays","author":"Barbisan","year":"2026","journal-title":"arXiv:2601.15433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref13","article-title":"High fidelity neural audio compression","author":"Defossez","year":"2022","journal-title":"arXiv:2210.13438"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2010.5461596"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30645-8_53"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616080"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304600"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007917"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.33682\/kfmf-zv94"},{"key":"ref22","article-title":"Dcase 2024 challenge task 10 development dataset: Acoustic-based traffic monitoring","author":"Bondi","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref24","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref25","article-title":"Discrete audio tokens: More than a survey!","author":"Mousavi","year":"2025","journal-title":"arXiv:2506.10274"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171604"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref28","article-title":"InstrumentGen: Generating sample-based musical instruments from text","author":"Nercessian","year":"2023","journal-title":"arXiv:2311.04339"},{"key":"ref29","article-title":"Vamp-Net: Music generation via masked acoustic token modeling","author":"Flores Garcia","year":"2023","journal-title":"arXiv:2307.04686"},{"key":"ref30","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv:2301.02111"},{"key":"ref31","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref33","article-title":"Metrics for multi-class classification: An overview","author":"Grandini","year":"2020","journal-title":"arXiv:2008.05756"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3579310"},{"key":"ref36","author":"Yamagishi","year":"2012","journal-title":"English Multi-Speaker Corpus for Cstr Voice Cloning Toolkit"},{"key":"ref37","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2379648"},{"key":"ref39","article-title":"The musdb18 corpus for music separation","volume-title":"Proc. ICML","author":"Rafii"},{"key":"ref40","first-page":"1","article-title":"The MTG\u2013Jamendo dataset for automatic music tagging","volume-title":"Proc. ICML","author":"Bogdanov"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-05991-w"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11500606.pdf?arnumber=11500606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:48:41Z","timestamp":1778050121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11500606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3689044","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}