{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T11:58:07Z","timestamp":1790510287288,"version":"4.1.0"},"reference-count":42,"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.2019.8683587","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"8623-8627","source":"Crossref","is-referenced-by-count":16,"title":["Multimodal One-shot Learning of Speech and Images"],"prefix":"10.1109","author":[{"given":"Ryan","family":"Eloff","sequence":"first","affiliation":[{"name":"E&#x0026;E Engineering, Stellenbosch University, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Herman A.","family":"Engelbrecht","sequence":"additional","affiliation":[{"name":"E&#x0026;E Engineering, Stellenbosch University, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"E&#x0026;E Engineering, Stellenbosch University, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref38","article-title":"TIDIGITS LDC93S10","author":"leonard","year":"1993"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268967"},{"key":"ref32","article-title":"Learning digits via joint audio-visual representations","author":"kashyap","year":"2017","journal-title":"M S thesis"},{"key":"ref31","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Proc NIPS"},{"key":"ref30","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref36","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref34","first-page":"89","article-title":"Semantic speech retrieval with a visually grounded model of untran-scribed speech","volume":"27","author":"kamper","year":"2019","journal-title":"IEEE Trans on ASLP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1013"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref11","article-title":"Signature verification using a &#x201D;Siamese\" time delay neural network","author":"bromley","year":"1994","journal-title":"Proc NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref13","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"chechik","year":"2010","journal-title":"JMLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref15","article-title":"Multilingual distributed representations without word alignment","author":"hermann","year":"2014","journal-title":"Proc ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref18","article-title":"In defense of the triplet loss for person re-identification","author":"hermans","year":"2017","journal-title":"arXiv preprint arXiv 1703 07737"},{"key":"ref19","article-title":"One-shot learning of generative speech concepts","author":"lake","year":"2014","journal-title":"Proc COGSCII"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/a0039702"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_32"},{"key":"ref3","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"2015","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911435515"},{"key":"ref29","article-title":"One-shot learning by inverting a compositional causal process","author":"lake","year":"2013","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"ref8","article-title":"Recognizing unfamiliar gestures for human-robot interaction through zero-shot learning","author":"thomason","year":"2016","journal-title":"Proc ISER"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1164622"},{"key":"ref2","article-title":"One shot learning of simple visual concepts","author":"lake","year":"2011","journal-title":"Proc COGSCII"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2633812"},{"key":"ref20","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc NIPS"},{"key":"ref22","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc NIPS"},{"key":"ref21","article-title":"Attentive recurrent comparators","author":"shyam","year":"2017","journal-title":"Proc ICML"},{"key":"ref24","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc ICML"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref23","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"2016","journal-title":"Proc ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref26","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"2017","journal-title":"Proc Robot Learn"},{"key":"ref25","article-title":"A simple neural attentive meta-learner","author":"mishra","year":"2018","journal-title":"Proc ICLR"}],"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\/08683587.pdf?arnumber=8683587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:19:23Z","timestamp":1757009963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683587","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}