{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:42:45Z","timestamp":1760132565639,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation of South Africa","award":["120409"],"award-info":[{"award-number":["120409"]}]},{"name":"Google Faculty Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.2973798","type":"journal-article","created":{"date-parts":[[2020,2,13]],"date-time":"2020-02-13T22:25:46Z","timestamp":1581632746000},"page":"421-425","source":"Crossref","is-referenced-by-count":11,"title":["Unsupervised Feature Learning for Speech Using Correspondence and Siamese Networks"],"prefix":"10.1109","volume":"27","author":[{"given":"Petri-Johan","family":"Last","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8753-8994","authenticated-orcid":false,"given":"Herman A.","family":"Engelbrecht","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-3475","authenticated-orcid":false,"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"821","article-title":"Rapid evaluation of speech representations for spoken term discovery","author":"carlin","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref38","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1665"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2334"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"article-title":"Representation learning for unsupervised speech processing","year":"2016","author":"renshaw","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref35","article-title":"Multilingual distributed representations without word alignment","author":"hermann","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269011"},{"article-title":"ABX-discriminability measures and applications","year":"2016","author":"schatz","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDP7175"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref14","first-page":"3174","article-title":"Discovering discrete subword units with binarized autoencoders and hidden-Markov-model encoders","author":"badino","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","first-page":"3199","article-title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461648"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1518"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078558"},{"key":"ref19","first-page":"3179","article-title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","author":"thiolli\u00e8re","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179087"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1592"},{"key":"ref27","first-page":"1781","article-title":"Evaluating speech features with the minimal-pair ABX task: Analysis of the classical MFC\/PLP pipeline","author":"schatz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179089"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639245"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.031"},{"key":"ref7","first-page":"3169","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-811"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/08998226.pdf?arnumber=8998226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:48:30Z","timestamp":1651070910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8998226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.2973798","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2020]]}}}