{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:17:03Z","timestamp":1753600623851,"version":"3.37.3"},"reference-count":22,"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"}],"funder":[{"DOI":"10.13039\/100017567","name":"Apple","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447515","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8090-8094","source":"Crossref","is-referenced-by-count":2,"title":["Audio-Visual Child-Adult Speaker Classification in Dyadic Interactions"],"prefix":"10.1109","author":[{"given":"Anfeng","family":"Xu","sequence":"first","affiliation":[{"name":"University of Southern California,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiantian","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Tager-Flusberg","sequence":"additional","affiliation":[{"name":"Boston University,Boston,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.ss7202a1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/t17256-000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/aur.2380"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-54587-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1273"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-07299-w"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref9","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conf. on Machine Learning","author":"Radford"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846253"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2078"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053251"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1447"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fcomm.2022.820564"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/aur.2883"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874254"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10447515.pdf?arnumber=10447515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:45:26Z","timestamp":1722577526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447515","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}