{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T01:53:05Z","timestamp":1771033985871,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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":[[2025,9,16]]},"DOI":"10.1109\/icdl63968.2025.11204445","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:07:41Z","timestamp":1761066461000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Assessing Whisper for Infant Research: Benchmarking ASR Accuracy and Failure Analysis on Caregiver-Infant Interactions"],"prefix":"10.1109","author":[{"given":"Yueyan","family":"Tang","sequence":"first","affiliation":[{"name":"University of California San Diego,Department of Cognitive Science,La Jolla,United States"}]},{"given":"Victoria","family":"Hennessy","sequence":"additional","affiliation":[{"name":"University of California San Diego,Department of Cognitive Science,La Jolla,United States"}]},{"given":"Tairan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California San Diego,Department of Cognitive Science,La Jolla,United States"}]},{"given":"Gedeon","family":"De\u00e1k","sequence":"additional","affiliation":[{"name":"University of California San Diego,Department of Cognitive Science,La Jolla,United States"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS 2020)","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/desc.12770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-024-02493-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-020-01393-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/lnc3.12015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/desc.12122"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/09637214211059536"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2007.00532.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0163-6383(87)90017-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0163-6383(85)80005-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-023-02127-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/cdev.13495"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s23187930"},{"key":"ref14","article-title":"The LENA Natural Language Study","author":"Gilkerson","year":"2008a"},{"key":"ref15","article-title":"Transcriptional analyses of the LENA natural language corpus","author":"Gilkerson","year":"2008b"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X0999152X"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-023-02206-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC53108.2024.10782773"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jecp.2017.04.017"},{"key":"ref20","article-title":"Whisper: Robust speech recognition via large language models"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-020-01460-x"},{"key":"ref22","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2012.00143"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1111\/infa.12545"},{"key":"ref26","article-title":"Annotation by category - ELAN and ISO DCR","volume-title":"Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008)","author":"Sloetjes"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDL61372.2024.10644508"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcn.2023.101283"},{"issue":"146","key":"ref29","first-page":"10","article-title":"Converting video formats with FFmpeg","volume":"2006","author":"Tomar","year":"2006","journal-title":"Linux Journal"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0956797614531023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1353\/aad.2017.0028"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.77399"}],"event":{"name":"2025 IEEE International Conference on Development and Learning (ICDL)","location":"Prague, Czech Republic","start":{"date-parts":[[2025,9,16]]},"end":{"date-parts":[[2025,9,19]]}},"container-title":["2025 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204361\/11204347\/11204445.pdf?arnumber=11204445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:42:38Z","timestamp":1761111758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204445\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icdl63968.2025.11204445","relation":{},"subject":[],"published":{"date-parts":[[2025,9,16]]}}}