{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T11:06:07Z","timestamp":1782817567069,"version":"3.54.5"},"reference-count":26,"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\/icassp48485.2024.10446424","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"691-695","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Modal Continual Pre-Training For Audio Encoders"],"prefix":"10.1109","author":[{"given":"Gyuhak","family":"Kim","sequence":"first","affiliation":[{"name":"University of Illinois at Chicago"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho-Hsiang","family":"Wu","sequence":"additional","affiliation":[{"name":"USA - Bosch Center for Artificial Intelligence,Bosch Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Bondi","sequence":"additional","affiliation":[{"name":"USA - Bosch Center for Artificial Intelligence,Bosch Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Illinois at Chicago"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref9","article-title":"Continual pre-training of language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ke"},{"key":"ref10","first-page":"29440","article-title":"Climb: A continual learning benchmark for vision-andlanguage tasks","volume":"35","author":"Srinivasan","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00940"},{"key":"ref14","article-title":"Continual vision-language representaion learning with off-diagonal information","author":"Ni","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref20","first-page":"125","article-title":"Hear: Holistic evaluation of audio representations","volume-title":"NeurIPS 2021 Competitions and Demonstrations Track","author":"Turian"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097117"}],"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\/10446424.pdf?arnumber=10446424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:15:39Z","timestamp":1722575739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446424","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}