{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:07:01Z","timestamp":1729634821661,"version":"3.28.0"},"reference-count":10,"publisher":"IEEE Comput. Soc","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/icmi.2002.1166977","type":"proceedings-article","created":{"date-parts":[[2003,6,26]],"date-time":"2003-06-26T01:03:42Z","timestamp":1056589422000},"page":"105-110","source":"Crossref","is-referenced-by-count":0,"title":["Towards visually-grounded spoken language acquisition"],"prefix":"10.1109","author":[{"given":"D.","family":"Roy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3608.001.0001","author":"regier","year":"1996","journal-title":"The Human Semantic Potential"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075242"},{"journal-title":"Spontaneous Speech Recognition Using Hidden Markov Models","year":"2001","author":"yoder","key":"ref10"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(02)00024-4"},{"key":"ref5","article-title":"Learning visually grounded words and syntax of natural spoken language","volume":"4","author":"roy","year":"2000","journal-title":"Evolution of Communication"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2601_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2003.811618"},{"journal-title":"Generating Referring Expressions Constructing Descriptions in a Domain of Objects and Processes","year":"1992","author":"dale","key":"ref2"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/ISIU.1999.824909","article-title":"Learning audio-visual associations from sensory input","author":"roy","year":"1999","journal-title":"Proceedings of the International Conference of Computer Vision Workshop on the Integration of Speech and Image Understanding"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00849177"}],"event":{"name":"Fourth IEEE International Conference on Multimodal Interfaces","acronym":"ICMI-02","location":"Pittsburgh, PA, USA"},"container-title":["Proceedings. Fourth IEEE International Conference on Multimodal Interfaces"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8346\/26309\/01166977.pdf?arnumber=1166977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:07:08Z","timestamp":1602688028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/1166977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/icmi.2002.1166977","relation":{},"subject":[]}}