{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:49:28Z","timestamp":1766083768694,"version":"3.48.0"},"reference-count":63,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272289"],"award-info":[{"award-number":["62272289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["D20031"],"award-info":[{"award-number":["D20031"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3616585","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:56:06Z","timestamp":1760032566000},"page":"4748-4763","source":"Crossref","is-referenced-by-count":0,"title":["Collaborative Transformer Prototype Network With Pretrained Contrastive Language-Audio Encoder for Open Set Audio Recognition"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4918-1411","authenticated-orcid":false,"given":"Haiyan","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9548-0411","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7636-3797","authenticated-orcid":false,"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Engineering, Institute of Science Tokyo, Yokohama 226-8501, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7191-3400","authenticated-orcid":false,"given":"Di","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Design Art & Media, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7933-8358","authenticated-orcid":false,"given":"Xingwei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Design Art & Media, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7314-6754","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5278-2006","authenticated-orcid":false,"given":"Yufeng","family":"Hua","sequence":"additional","affiliation":[{"name":"Nanjing School for the Deaf, Naning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3226-3978","authenticated-orcid":false,"given":"Jun","family":"Shi","sequence":"additional","affiliation":[{"name":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IST55454.2022.9827729"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096787"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2018.8326315"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5093-5_33"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-01045-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3280011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746056"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447726"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3502287"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2613924"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00414"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_38"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3445182"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5326.661099"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.58325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137622"},{"key":"ref30","first-page":"405","article-title":"Clustering by means of medoids","volume-title":"Proc. Statist. Data Anal. L1 Norm Conf.","author":"Rdusseeun","year":"1987"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009769707641"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1998.711145"},{"key":"ref34","first-page":"423","article-title":"Generalized learning vector quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"8","author":"Sato","year":"1995"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/78.553484"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1996.547612"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(96)00072-6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00366"},{"key":"ref39","first-page":"8930","article-title":"This looks like that: deep learning for interpretable image recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Chen","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070850"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2025.103081"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3106743"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3359238"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3408048"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3351439"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.surge.2010.01.006"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3189996"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref56","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technologies, Volume 1 (Long Short Papers),","author":"Kim","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.10.019"},{"key":"ref61","first-page":"9157","article-title":"Reducing network agnostophobia","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Dhamija","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200384"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-71693-9"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11197581.pdf?arnumber=11197581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:35:44Z","timestamp":1766082944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3616585","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2025]]}}}