{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T20:51:52Z","timestamp":1792443112824,"version":"4.5.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404800","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"237-244","source":"Crossref","is-referenced-by-count":73,"title":["Deep multimodal semantic embeddings for speech and images"],"prefix":"10.1109","author":[{"given":"David","family":"Harwath","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"girshick","year":"2013","journal-title":"Proceedings of the 2013 Conference on Computer Vision and Pattern Recognition CVPR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref12","article-title":"Word embeddings for speech recognition","author":"bengio","year":"2014","journal-title":"Proceedings of the Conference of the International Speech Communication Association-Interspeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref14","article-title":"Collecting image annotations using amazon's mechanical turk","author":"rashtchian","year":"2010","journal-title":"Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","author":"young","year":"2014","journal-title":"Association of Computational Linguistics"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014"},{"key":"ref17","article-title":"Spoke: A framework for building speech-enabled websites","author":"saylor","year":"2015"},{"key":"ref18","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.455"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref5","article-title":"A joint model of language and perception for grounded attribute learning","author":"matuszek","year":"2012","journal-title":"International Conference on Machine Learning (ICML) 2012"},{"key":"ref8","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proceedings of the 2015 Conference on Computer Vision and Pattern Recognition CVPR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref1","article-title":"Matching words and pictures","author":"barnard","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Neural Inf Process Soc"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref22","article-title":"Improving word representations via global context and multiple word prototypes","author":"huang","year":"2012","journal-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1162\/tacl_a_00177","article-title":"Grounded compositional semantics for finding and describing images with sentences","author":"socher","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","location":"Scottsdale, AZ, USA","start":{"date-parts":[[2015,12,13]]},"end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404800.pdf?arnumber=7404800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,4]],"date-time":"2019-09-04T14:03:41Z","timestamp":1567605821000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404800","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}