{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:16:17Z","timestamp":1776467777213,"version":"3.51.2"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683069","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"8618-8622","source":"Crossref","is-referenced-by-count":9,"title":["Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese"],"prefix":"10.1109","author":[{"given":"William N.","family":"Havard","sequence":"first","affiliation":[{"name":"LIG, Univ. Grenoble Alpes, CNRS, Grenoble, 38000, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Pierre","family":"Chevrot","sequence":"additional","affiliation":[{"name":"LIDILEM, Univ. Grenoble Alpes, Grenoble, 38000, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Besacier","sequence":"additional","affiliation":[{"name":"LIG, Univ. Grenoble Alpes, CNRS, Grenoble, 38000, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1303"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00300"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-502","article-title":"Visually grounded learning of keyword prediction from untranscribed speech","author":"kamper","year":"2017","journal-title":"InterSpeech"},{"key":"ref14","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Advances in Neural Information Processing Systems 29 Annual Conference on Neural Information Processing Systems 2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2017.11.008"},{"key":"ref16","author":"gibson","year":"1969","journal-title":"Principles of Perceptual Learning and Development"},{"key":"ref17","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR-2015"},{"key":"ref18","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"INTER-SPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1057"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1037"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Computer Vision – ECCV 2014"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref20","first-page":"154","article-title":"Probabilistic part-of-speech tagging using decision trees","author":"schmid","year":"1997","journal-title":"New Methods in Language Processing"},{"key":"ref22","article-title":"A universal part-of-speech tagset","author":"petrov","year":"2012","journal-title":"Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC)"},{"key":"ref21","first-page":"529","article-title":"Point-wise prediction for robust, adaptable japanese morphological analysis","author":"neubig","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2015.11.007"},{"key":"ref23","first-page":"301","article-title":"Why nouns are learned before verbs: Linguistic relativity versus natural partitioning","volume":"2","author":"gentner","year":"1982","journal-title":"Language"},{"key":"ref25","author":"ferguson","year":"1973","journal-title":"Study of Child Language Development"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683069.pdf?arnumber=8683069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:14:47Z","timestamp":1756754087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683069","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}