{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T18:02:40Z","timestamp":1762624960571,"version":"3.37.3"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T00:00:00Z","timestamp":1667606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T00:00:00Z","timestamp":1667606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801241,62071242"],"award-info":[{"award-number":["61801241,62071242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20180746"],"award-info":[{"award-number":["BK20180746"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M711693"],"award-info":[{"award-number":["2022M711693"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"DFG (German Research Foundation)","doi-asserted-by":"publisher","award":["442218748"],"award-info":[{"award-number":["442218748"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,5]]},"DOI":"10.1109\/cisp-bmei56279.2022.9980329","type":"proceedings-article","created":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T18:59:19Z","timestamp":1671649159000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Zero-Shot Audio Classification Using Synthesised Classifiers and Pre-Trained Models"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Gu","sequence":"first","affiliation":[{"name":"School of Internet of Things, Nanjing University of Posts and Telecommunications,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinzhou","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Internet of Things, Nanjing University of Posts and Telecommunications,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bjorn","family":"Schuller","sequence":"additional","affiliation":[{"name":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909479"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2199972"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118753"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref7","article-title":"Rethinking CNN models for audio classification","author":"Palanisamy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616340"},{"key":"ref12","article-title":"Audio captioning using gated recurrent units","author":"Eren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.09.014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.anbehav.2020.06.004"},{"key":"ref16","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","author":"Socher","year":"2013","journal-title":"Advances in Neural Information Processing Systems 26. Curran Associates, Inc."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087098"},{"journal-title":"Zero-shot learning for speech recognition with universal phonetic model","year":"2018","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414478"},{"key":"ref23","first-page":"5210","article-title":"Auto VC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Qian"},{"key":"ref24","first-page":"70","article-title":"Zero-shot singing voice conversion","volume-title":"Proc. Inter-national Society for Music Information Retrieval Conference (ISMIR)","author":"Nercessian"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2406"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3130401"},{"key":"ref27","first-page":"67","article-title":"Zero-shot learning for audio-based music classification and tagging","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Choi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937283"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414994"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2264"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01193-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00793"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.575"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-32"},{"key":"ref38","first-page":"3111","article-title":"Dis-tributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013","journal-title":"Advances in Neural Information Processing Systems 26. Curran Associates, Inc."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682743"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462168"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1969"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"issue":"1","key":"ref43","first-page":"6340","article-title":"auDeep: Unsupervised learning of representations from audio with deep recurrent neural networks","volume":"18","author":"Freitag","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"}],"event":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","start":{"date-parts":[[2022,11,5]]},"location":"Beijing, China","end":{"date-parts":[[2022,11,7]]}},"container-title":["2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9979807\/9979817\/09980329.pdf?arnumber=9980329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:08:25Z","timestamp":1706767705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9980329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,5]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/cisp-bmei56279.2022.9980329","relation":{},"subject":[],"published":{"date-parts":[[2022,11,5]]}}}