{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:33:57Z","timestamp":1762342437366,"version":"3.38.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111700"],"award-info":[{"award-number":["2021ZD0111700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62137002","62176245"],"award-info":[{"award-number":["62137002","62176245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521837","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:21:58Z","timestamp":1735068118000},"page":"1114-1126","source":"Crossref","is-referenced-by-count":1,"title":["Investigating the Effective Dynamic Information of Spectral Shapes for Audio Classification"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6558-7522","authenticated-orcid":false,"given":"Liangwei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6323-5662","authenticated-orcid":false,"given":"Xiren","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"given":"Qiuju","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3192-1994","authenticated-orcid":false,"given":"Fang","family":"Xiong","sequence":"additional","affiliation":[{"name":"National Clinical Research Center for Geriatric Diseases, Department of Otolaryngology Head and Neck Surgery, Xiangya Hospital, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3918-384X","authenticated-orcid":false,"given":"Huanhuan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840604"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860487"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(03)00147-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2993152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106073"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035275"},{"key":"ref7","article-title":"Mel frequency cepstral coefficients for music modeling","volume-title":"Proc. Int. Symp. Music Inf. Retrieval","author":"Logan","year":"2000"},{"key":"ref8","first-page":"616","article-title":"Speech-music discrimination: A deep learning perspective","volume-title":"Proc. 22nd Eur. Signal Process. Conf.","author":"Pikrakis","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414000"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.08.250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3280011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487700"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2256797"},{"key":"ref14","first-page":"3387","article-title":"Model metric co-learning for time series classification","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Chen","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref17","first-page":"1","article-title":"Harmonic\/percussive separation using median filtering","volume-title":"Proc. 13th Int. Conf. Digit. Audio Effects","author":"Fitzgerald","year":"2010"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.12"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854048"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2015.09.005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.06.005"},{"key":"ref23","article-title":"Unsupervised learning of low-level audio features for music similarity estimation","volume-title":"Proc. Workshop Learn. Architectures, Representations, Optim. Speech Vis. Inf. Process.","author":"Osendorfer","year":"2011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2355774"},{"key":"ref25","first-page":"1","article-title":"Beat histogram features for rhythm-based musical genre classification using multiple novelty functions","volume-title":"Proc. 18th Int. Conf. Digital Audio Effects","author":"Lykartsis","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.05.016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118041"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892651"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3244507"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889714"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00297"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2014.03.015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3200153"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3344721"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2799586"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2592679"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jappgeo.2018.01.006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3347739"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2789422"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116879"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113071"},{"issue":"34","key":"ref47","article-title":"The echo state approach to analysing and training recurrent neural networks-with an erratum note","volume-title":"Bonn, Germany: German Nat. Res. Center Inf. Technol. GMD Tech. Rep.","volume":"148","author":"Jaeger","year":"2001"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2089641"},{"key":"ref49","first-page":"778","article-title":"Predictive modeling with echo state networks","volume-title":"Proc. Int. Conf. Artif. Neural Netw.","author":"eransky","year":"2008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.11.076"},{"key":"ref51","first-page":"618","article-title":"Comparison of echo state networks with simple recurrent networks and variable-length markov models on symbolic sequences","volume-title":"Proc. Int. Conf. Artif. Neural Netw.","author":"eransky","year":"2007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.872357"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488635"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(79)90072-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1983.1056714"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(79)90069-3"},{"article-title":"Musan: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref57"},{"key":"ref58","first-page":"528","article-title":"A benchmark dataset for audio classification and clustering","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Homburg","year":"2005"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00886-3"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814068.pdf?arnumber=10814068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:44:37Z","timestamp":1741715077000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521837","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}