{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:15:59Z","timestamp":1784391359682,"version":"3.55.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448504","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"336-340","source":"Crossref","is-referenced-by-count":64,"title":["Natural Language Supervision For General-Purpose Audio Representations"],"prefix":"10.1109","author":[{"given":"Benjamin","family":"Elizalde","sequence":"first","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soham","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaming","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"HEAR: Holistic Evaluation of Audio Representations","author":"Turian","year":"2022","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1136"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref10","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref13","article-title":"AudioCaps: Generating Captions for Audios in The Wild","author":"Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref16","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"},{"key":"ref17","article-title":"Fma: A dataset for music analysis","volume-title":"18th International Society for Music Information Retrieval Conference","author":"Defferrard"},{"key":"ref18","article-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979822"},{"key":"ref24","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref26","article-title":"A short note on the kinetics-700-2020 human action dataset","author":"Smaira","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096877"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448504.pdf?arnumber=10448504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:54Z","timestamp":1722660894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448504","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}