{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:05Z","timestamp":1775229905490,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["120409"],"award-info":[{"award-number":["120409"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"James S. McDonnell Foundation Scholar","award":["220020374"],"award-info":[{"award-number":["220020374"]}]},{"name":"James S. McDonnell Foundation Scholar","award":["ES\/R006660\/1"],"award-info":[{"award-number":["ES\/R006660\/1"]}]},{"name":"Google Faculty Award for HK"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3060805","type":"journal-article","created":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T23:54:15Z","timestamp":1614038055000},"page":"1107-1118","source":"Crossref","is-referenced-by-count":10,"title":["Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer"],"prefix":"10.1109","volume":"29","author":[{"given":"Herman","family":"Kamper","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yevgen","family":"Matusevych","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharon","family":"Goldwater","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Acoustic word embedding system for code-switching query-by-example spoken term detection","author":"ma","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683868"},{"key":"ref31","article-title":"Contextual joint factor acoustic embeddings","author":"shi","year":"0","journal-title":"Proc Spoken Lang Technol"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682553"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682903"},{"key":"ref36","article-title":"Multi-view recurrent neural acoustic word embeddings","author":"he","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2511"},{"key":"ref34","first-page":"1053","article-title":"Word embeddings for speech recognition","author":"bengio","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054202"},{"key":"ref64","first-page":"821","article-title":"Rapid evaluation of speech representations for spoken term discovery","author":"carlin","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","article-title":"Improved audio embeddings by adjacency-based clustering with applications in spoken term detection","author":"huang","year":"2018"},{"key":"ref65","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":"ref66","article-title":"Analyzing autoencoder-based acoustic word embeddings","author":"matusevych","year":"0","journal-title":"Proc BAICS Workshop Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2364"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.031"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639245"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2759726"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1592"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639553"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683275"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846310"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.001"},{"key":"ref59","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"chechik","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref58","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"weinberger","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref56","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref55","article-title":"Neural transfer learning for natural language processing","author":"ruder","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179089"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462002"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2828"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1112"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00146"},{"key":"ref15","first-page":"3204","article-title":"Unsupervised word discovery from speech using automatic segmentation into syllable-like units","author":"r\u00e4s\u00e4nen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163164"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"},{"key":"ref19","first-page":"765","article-title":"Unsupervised learning of audio segment representations using sequence-to-sequence recurrent neural networks","author":"chung","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDP7175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2973798"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2384"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.04.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1665"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101098"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00094-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2224"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638959"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288862"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953237"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09360516.pdf?arnumber=9360516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:55Z","timestamp":1652194435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9360516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3060805","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}