{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T17:23:12Z","timestamp":1773681792821,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1736210"],"award-info":[{"award-number":["U1736210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61471145"],"award-info":[{"award-number":["61471145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.2996085","type":"journal-article","created":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T20:20:10Z","timestamp":1590006010000},"page":"950-954","source":"Crossref","is-referenced-by-count":32,"title":["Learning Temporal Relations from Semantic Neighbors for Acoustic Scene Classification"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8457-2943","authenticated-orcid":false,"given":"Liwen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4297-4300","authenticated-orcid":false,"given":"Jiqing","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3105-6213","authenticated-orcid":false,"given":"Ziqiang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1989"},{"key":"ref11","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","article-title":"AclNet: Efficient end-to-end audio classification CNN%","author":"huang","year":"2018","journal-title":"CoRR"},{"key":"ref14","first-page":"103?107","article-title":"Exploring deep vision models for acoustic scene classification","author":"octave","year":"0","journal-title":"Proc Detect Classif Acoust Sce Events 2018 Workshop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.33682\/8rd2-g787"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683288"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.33682\/8xh4-jm46"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683434"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.33682\/6c9z-gd15"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2013.042313.00197"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00440"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.03.004"},{"key":"ref6","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"heittola","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9_3"},{"key":"ref5","article-title":"Content analysis for acoustic environment classification in mobile robots","author":"chu","year":"0","journal-title":"Proc AAAI Fall Symp"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref7","first-page":"9?13","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"0","journal-title":"Proc Detect Classif Acoust Sce Events 2018 Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2699334"},{"key":"ref9","first-page":"113?117","article-title":"DNN based multi-level feature ensemble for acoustic scene classification","author":"jung","year":"0","journal-title":"Proc Detect Classif Acoust Sce Events 2018 Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2966868"},{"key":"ref22","first-page":"155","article-title":"Support vector regression machines","volume":"9","author":"drucker","year":"1997","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref21","first-page":"3284","article-title":"Unsupervised temporal feature learning based on sparse coding embedded BoAW","author":"zhang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"583","article-title":"Music\/voice separation using the similarity matrix","author":"rafii","year":"0","journal-title":"Proc ISMIR"},{"key":"ref23","first-page":"34?38","article-title":"Acoustic scene classification using a convolutional neural network ensemble and nearest neighbor filters","author":"truc","year":"0","journal-title":"Proc Detect Classif Acoust Sce Events 2018 Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09097422.pdf?arnumber=9097422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:48:10Z","timestamp":1651070890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9097422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.2996085","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}