{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T17:04:29Z","timestamp":1768410269274,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["AB 675\/2-2"],"award-info":[{"award-number":["AB 675\/2-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["MU 2686\/11-2"],"award-info":[{"award-number":["MU 2686\/11-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3293032","type":"journal-article","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T17:26:55Z","timestamp":1689096415000},"page":"2658-2667","source":"Crossref","is-referenced-by-count":3,"title":["How Robust are Audio Embeddings for Polyphonic Sound Event Tagging?"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4689-7944","authenticated-orcid":false,"given":"Jakob","family":"Abe\u00dfer","sequence":"first","affiliation":[{"name":"Fraunhofer IDMT, Ilmenau, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9703-110X","authenticated-orcid":false,"given":"Sascha","family":"Grollmisch","sequence":"additional","affiliation":[{"name":"Fraunhofer IDMT, Ilmenau, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-7524","authenticated-orcid":false,"given":"Meinard","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref17","first-page":"640","article-title":"Contrastive audio-language learning for music","author":"manco","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref16","first-page":"1","article-title":"A model ensemble approach for audio-visual scene classification","author":"wang","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909904"},{"key":"ref18","first-page":"777","article-title":"Emotion embedding spaces for matching music to stories","author":"won","year":"0","journal-title":"Proc Soc Music Inf Retrieval Conf"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref45","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref42","article-title":"Librosa\/Librosa: 0.8.0","author":"mcfee","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925883"},{"key":"ref44","first-page":"609","article-title":"Look, listen and learn","author":"arandjelovi?","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/01969727308546046"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053396"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287743"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892893"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00034"},{"key":"ref35","first-page":"125","article-title":"HEAR: Holistic evaluation of audio representations","author":"turian","year":"0","journal-title":"Proc NeurIPS Competitions Demonstrations Track"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413555"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3032060"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2632307"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746489"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3293015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909611"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461396"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909557"},{"key":"ref24","first-page":"1","article-title":"Generative timbre spaces: Regularizing variational auto-encoders with perceptual metrics","author":"esling","year":"0","journal-title":"Proc Int Conf Digit Audio Effects"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA53542.2021.9686838"},{"key":"ref26","first-page":"1","article-title":"Incorporating auxiliary data for urban sound tagging","author":"iqbal","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414229"},{"key":"ref22","article-title":"Jukebox: A. generative model for music","author":"dhariwal","year":"2020"},{"key":"ref21","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","author":"engel","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632677"},{"key":"ref27","first-page":"150","article-title":"Active learning for sound event classification using monte-carlo dropout and PANN embeddings","author":"shishkin","year":"0","journal-title":"Proc Workshop Detection Classification Acoust Scenes Events"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2020.00014"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10178070.pdf?arnumber=10178070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T18:23:17Z","timestamp":1691432597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10178070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3293032","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}