{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T05:36:15Z","timestamp":1790228175269,"version":"4.1.0"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1816627"],"award-info":[{"award-number":["1816627"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/taslp.2018.2872106","type":"journal-article","created":{"date-parts":[[2018,9,24]],"date-time":"2018-09-24T21:41:07Z","timestamp":1537825267000},"page":"89-98","source":"Crossref","is-referenced-by-count":26,"title":["Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-3475","authenticated-orcid":false,"given":"Herman","family":"Kamper","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Shakhnarovich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289082"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.08.012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2009.02335.x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(96)00728-7"},{"key":"ref30","first-page":"1309","article-title":"From phonemes to images: Levels of representation in a recurrent neural model of\n visually-grounded language learning","author":"gelderloos","year":"0","journal-title":"Proc Int Conf Comput Linguistics"},{"key":"ref37","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"0","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.procs.2016.04.031","article-title":"The zero resource speech challenge 2015:\n Proposed approaches and results","volume":"81","author":"versteegh","year":"2016","journal-title":"Proc Journal of Computer Science"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639245"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2010.07.036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1609179.1609180"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1037\/a0039702"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"3677","DOI":"10.21437\/Interspeech.2017-502","article-title":"Visually grounded\n learning of keyword prediction from untranscribed speech","author":"kamper","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/17470210902888809"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2007.01915.x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2601_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2010.01118.x"},{"key":"ref26","first-page":"1481","article-title":"A computational model for unsupervised word discovery","author":"bosch","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref100","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1008722.1008727"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4135"},{"key":"ref58","first-page":"1423","article-title":"Grounded models of semantic representation","author":"silberer","year":"0","journal-title":"Proc Joint Conf Empirical Methods Natural Lang Process Comput Natural Lang Learn"},{"key":"ref57","first-page":"91","article-title":"Visual information in semantic representation","author":"feng","year":"0","journal-title":"Proc 2010 Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"ref55","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with\n visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00146"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref3","article-title":"Query-by-example search with\n discriminative neural acoustic word embeddings","author":"settle","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","first-page":"53","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2076"},{"key":"ref8","first-page":"613","article-title":"Representations of language in a model of visually grounded speech signal","author":"chrupa?a","year":"0","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-968"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79547-6_52"},{"key":"ref46","first-page":"1889","article-title":"Deep\n fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref48","first-page":"444","article-title":"Corpus-guided sentence\n generation of natural images","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref47","first-page":"15","article-title":"Every picture tells a story: Generating\n sentences from images","author":"farhadi","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref42","article-title":"Unsupervised neural and bayesian models for zero-resource speech\n processing","author":"kamper","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2517567"},{"key":"ref44","first-page":"2764","article-title":"WSABIE:\n Scaling up to large vocabulary image annotation","author":"weston","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/29.103088"},{"key":"ref72","article-title":"Using word embeddings for automatic query expansion","author":"roy","year":"0","journal-title":"Proc SIGIR Workshop Neural Inf Retrieval"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1035"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref76","first-page":"1","article-title":"The TREC spoken document retrieval track: A success story","author":"garofolo","year":"0","journal-title":"Proc Content-Based Multimedia Inf Access-Volume 1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917992"},{"key":"ref74","first-page":"633","article-title":"Comparison of keyword spotting approaches for\n informal continuous speech","author":"sz\u00f6ke","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660179"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424219"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"ref60","first-page":"136","article-title":"Distributional semantics in technicolor","author":"bruni","year":"0","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1068"},{"key":"ref61","first-page":"1146","article-title":"A multimodal LDA model integrating textual, cognitive and visual modalities","author":"roller","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref63","first-page":"573","article-title":"Look, listen, and\n decode: Multimodal speech recognition with images","author":"sun","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref65","first-page":"2165","article-title":"Speech-based\n annotation and retrieval of digital photographs","author":"hazen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460127"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/243199.243202"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078558"},{"key":"ref69","first-page":"529","article-title":"The\n SphereSearch engine for unified ranked retrieval of heterogeneous XML and web documents","author":"graupmann","year":"0","journal-title":"Proc Int Conf Very Large Data Bases"},{"key":"ref1","first-page":"8","article-title":"Breaking the unwritten language barrier: The\n BULB project","author":"adda","year":"0","journal-title":"Proc Spoken Lang Technol Under-Resour Lang"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00237"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620758"},{"key":"ref92","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref90","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref98","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1162\/tacl_a_00143","article-title":"From paraphrase database to\n compositional paraphrase model and back","volume":"3","author":"wieting","year":"2015","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref99","article-title":"Towards universal paraphrastic sentence\n embeddings","author":"wieting","year":"0","journal-title":"Proc Proc International Conference on Learning Representations"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152306"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1164622"},{"key":"ref12","article-title":"Learning\n words from images and speech","author":"synnaeve","year":"0","journal-title":"Proc NIPS Workshop Learning Semantics"},{"key":"ref13","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref14","first-page":"613","article-title":"Representations of language in a model of visually grounded speech signal","author":"chrupa?a","year":"0","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-12"},{"key":"ref16","first-page":"424","article-title":"Learning\n modality-invariant representations for speech and images","author":"leidal","year":"2017","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461761"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639335"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01231-1_40","article-title":"Jointly discovering visual objects and spoken words from raw sensory input","author":"harwath","year":"2018"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"key":"ref83","first-page":"892","article-title":"SoundNet:\n Learning sound representations from unlabeled video","author":"aytar","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707729"},{"key":"ref89","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref85","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"ref87","first-page":"1274","article-title":"Fast\n image tagging","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/6570655\/8471003\/8471204-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8471003\/08471204.pdf?arnumber=8471204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:13:26Z","timestamp":1657746806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8471204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":100,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2872106","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}