{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:53Z","timestamp":1740169193353,"version":"3.37.3"},"reference-count":37,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001780","name":"RMIT University Postgraduate Scholarship","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2999055","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T21:32:05Z","timestamp":1591047125000},"page":"103327-103338","source":"Crossref","is-referenced-by-count":4,"title":["Learning Acoustic Word Embeddings With Dynamic Time Warping Triplet Networks"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0009-0985","authenticated-orcid":false,"given":"Denis","family":"Shitov","sequence":"first","affiliation":[]},{"given":"Elena","family":"Pirogova","sequence":"additional","affiliation":[]},{"given":"Tadeusz A.","family":"Wysocki","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7860-7289","authenticated-orcid":false,"given":"Margaret","family":"Lech","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"323","article-title":"The zero resource speech challenge 2017","author":"dunbar","year":"2017","journal-title":"Proc IEEE Workshop Autom Speech Recognition Understanding (ASRU)"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICASSP.1992.225858"},{"year":"2019","journal-title":"Creative Commons","key":"ref31"},{"key":"ref30","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018","journal-title":"arXiv 1804 03209"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"821","DOI":"10.21437\/Interspeech.2011-304","article-title":"Rapid evaluation of speech representations for spoken term discovery","author":"michael carlin","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref36","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/ICASSP.2015.7179090"},{"key":"ref34","first-page":"1","article-title":"Query-by-example spoken term detection on multilingual unconstrained speech","author":"mir\u00f3","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1109\/SLT.2016.7846310","article-title":"Discriminative acoustic word embeddings: Tecurrent neural network-based approaches","author":"settle","year":"2016","journal-title":"Proc IEEE Spoken Lang Technol Workshop (SLT)"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.21437\/Interspeech.2011-91","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref12","article-title":"Query-by-example search with discriminative neural acoustic word embeddings","author":"settle","year":"2017","journal-title":"arXiv 1706 03818"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP.2018.8462002"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2018-2341"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2019-3119"},{"key":"ref16","article-title":"Multi-view recurrent neural acoustic word embeddings","author":"he","year":"2016","journal-title":"arXiv 1611 04496"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICASSP.2015.7179091"},{"key":"ref19","article-title":"Soft-DTW: A differentiable loss function for time-series","author":"cuturi","year":"2017","journal-title":"arXiv 1703 01541"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.artmed.2008.11.007"},{"key":"ref27","article-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","author":"sak","year":"2014","journal-title":"arXiv 1402 1128"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1093\/bioinformatics\/17.6.495"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref29","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"ref8","article-title":"Deep convolutional acoustic word embeddings using word-pair side information","author":"kamper","year":"2015","journal-title":"arXiv 1510 01032"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2009.4960457"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/EUSIPCO.2015.7362666"},{"key":"ref9","article-title":"Learning word embeddings from speech","author":"chung","year":"2017","journal-title":"arXiv 1711 01515"},{"key":"ref1","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","author":"donald berndt","year":"1994","journal-title":"Proc Int'l Conf Knowledge Discovery and Data Mining"},{"year":"2019","author":"hua","journal-title":"PyTorch-SoftDTW","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"Deep metric learning using triplet network","author":"hoffer","year":"2015","journal-title":"Similarity-Based Pattern Recognition"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ASRU46091.2019.9003752"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICCV.2017.309"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref25","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09104974.pdf?arnumber=9104974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T19:06:22Z","timestamp":1643310382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9104974\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2999055","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}