{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:06:40Z","timestamp":1737176800916,"version":"3.33.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832254","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1165-1172","source":"Crossref","is-referenced-by-count":0,"title":["Measuring Sound Symbolism In Audio-Visual Models"],"prefix":"10.1109","author":[{"given":"Wei-Cheng","family":"Tseng","sequence":"first","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Jen","family":"Shih","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raymond","family":"Mooney","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref2","article-title":"Speechclip: Integrating speech with pre-trained vision and language model","author":"Shih","year":"2022","journal-title":"SLT"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747103"},{"key":"ref4","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"ICLR"},{"key":"ref5","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2023","journal-title":"ICLR"},{"key":"ref6","article-title":"Mavil: Masked audio-video learners","author":"Huang","year":"2023","journal-title":"NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389619"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1353\/nlh.1996.0031"},{"issue":"1","key":"ref11","article-title":"The tongues of men and speech","volume":"4","author":"Firth","year":"1968","journal-title":"Foundations of Language"},{"issue":"1","key":"ref12","doi-asserted-by":"crossref","first-page":"XVIII","DOI":"10.1007\/BF00422382","article-title":"Gestalt psychology","volume":"31","author":"k\u00f6hler","year":"1967","journal-title":"Psychologische forschung"},{"key":"ref13","first-page":"3","article-title":"Synaesthesiaawindow into perception, thought and language","volume":"8","author":"Ramachandran","journal-title":"J. Conscious. Stud"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/oseo\/instance.00018020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2012.09.007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0298"},{"key":"ref17","article-title":"Kiki or bouba? sound symbolism in vision-and-language models","author":"Alper","year":"2023","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.anthro.28.1.225"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2006.00495.x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2018.02.023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1075\/ill.16.02din"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5334\/gjgl.1646"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2307\/416653"},{"issue":"39","key":"ref25","doi-asserted-by":"crossref","first-page":"10818","DOI":"10.1073\/pnas.1605782113","article-title":"Sound-meaning association biases evidenced across thousands of languages","volume":"113","author":"dami\u00e1n","year":"2016","journal-title":"PNAS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2020.0390"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1515\/lingty-2019-0030"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008184423824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018","journal-title":"arXiv preprint arXiv:1807.03748"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447683"},{"key":"ref33","article-title":"Weakly-supervised audio-visual segmentation","author":"Mo","year":"2023","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445941"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-022-01516-2"},{"key":"ref36","first-page":"33428","article-title":"Toward a realistic model of speech processing in the brain with self-supervised learning","volume":"35","author":"Millet","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref40","article-title":"Blackboxnlp workshop"},{"issue":"3","key":"ref41","first-page":"1","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref44","article-title":"Axiomatic attribution for deep networks","volume":"abs\/1703.01365","author":"Sundararajan","year":"2017","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref46","article-title":"What do you learn from context? probing for sentence structure in contextualized word representations","author":"Tenney","year":"2019","journal-title":"ICLR"},{"key":"ref47","first-page":"4129","article-title":"A structural probe for finding syntax in word representations","author":"Hewitt","year":"2019","journal-title":"NAACL"},{"key":"ref48","article-title":"Understanding deep image representations by inverting them","volume":"abs\/1412.0035","author":"Mahendran","year":"2014","journal-title":"CoRR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.38"},{"key":"ref52","first-page":"1565","article-title":"Sound to meaning mappings in the bouba-kiki effect","volume":"2015","author":"McCormick","year":"2015","journal-title":"CogSci"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref54","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref55","article-title":"Unsupervised learning of spoken language with visual context","volume":"29","author":"Harwath","year":"2016","journal-title":"NIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref58","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv:1809.00496"},{"key":"ref59","article-title":"Learning state-aware visual representations from audible interactions","author":"Mittal","year":"2022","journal-title":"NIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref64","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"PMLR"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832254.pdf?arnumber=10832254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:42:03Z","timestamp":1737099723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832254","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}