{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:27:47Z","timestamp":1781609267612,"version":"3.54.5"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888245","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning"],"prefix":"10.1109","author":[{"given":"Tiago Fernandes","family":"Tavares","sequence":"first","affiliation":[{"name":"INSPER São Paulo,São Paulo,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Jos\u00e9 Ayres","sequence":"additional","affiliation":[{"name":"INSPER São Paulo,São Paulo,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhepei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Urbana,IL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paris","family":"Smaragdis","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Urbana,IL"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref3","article-title":"Query-by-Blending: A Music Exploration System Blending Latent Vector Representations of Lyric Word, Song Audio, and Artist","volume-title":"International Society for Music Information Retrieval Conference","author":"Watanabe"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref5","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1136"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref10","article-title":"Zero-shot Learning for Audio-based Music Classification and Tagging","volume-title":"International Society for Music Information Retrieval Conference","author":"Choi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"issue":"86","key":"ref13","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref15","article-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","author":"Ramesh","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref19","article-title":"Audiocaps: Generating captions for audios in the wild","author":"Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888245.pdf?arnumber=10888245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:46Z","timestamp":1774416226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888245","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}