{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T12:15:49Z","timestamp":1768997749141,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095091","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples"],"prefix":"10.1109","author":[{"given":"Hyeonggon","family":"Ryu","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arda","family":"Senocak","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"In","family":"So Kweon","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon","family":"Son Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1647"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-53"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-435"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846320"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01598"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1352"},{"key":"ref24","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"li","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref23","article-title":"Self-supervised co-training for video representation learning","author":"han","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747867"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053428"},{"key":"ref22","article-title":"Supervised contrastive learning","author":"khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref28","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3078"},{"key":"ref8","article-title":"Avlnet: Learning audio-visual language representations from instructional videos","author":"rouditchenko","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683275"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.244"},{"key":"ref4","article-title":"Representations of language in a model of visually grounded speech signal","author":"chrupa?a","year":"2017","journal-title":"Association for Computational Linguistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/SLTU.2018-53","article-title":"Visually grounded cross-lingual keyword spotting in speech","author":"kamper","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-502"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095091.pdf?arnumber=10095091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:27Z","timestamp":1700507367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095091","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}