{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:56:46Z","timestamp":1782313006975,"version":"3.54.5"},"reference-count":41,"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":"Swiss NSF"},{"name":"Parsimonious Hierarchical Automatic Speech Recognition and Query Detection","award":["200020-169398"],"award-info":[{"award-number":["200020-169398"]}]},{"name":"Learning Representations of Abstraction for Opinion Summarisation","award":["FNS-30216"],"award-info":[{"award-number":["FNS-30216"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2988788","type":"journal-article","created":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T19:56:47Z","timestamp":1587412607000},"page":"1416-1427","source":"Crossref","is-referenced-by-count":29,"title":["Neural Network Based End-to-End Query by Example Spoken Term Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-9199","authenticated-orcid":false,"given":"Dhananjay","family":"Ram","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lesly","family":"Miculicich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Herve","family":"Bourlard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Pytorch","author":"paszke","year":"2017"},{"key":"ref38","article-title":"Speechdat (e)-Eastern European telephone speech databases","author":"poll\u00e1k","year":"0","journal-title":"Proc of Workshop on Very Large Telephone Speech Databases"},{"key":"ref33","article-title":"Query-by-example spoken term detection evaluation on low-resource languages","author":"anguera","year":"0","journal-title":"Proc Int Workshop Spoken Lang Technol Under-Resourced Lang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"key":"ref31","first-page":"584","article-title":"Direct transfer of learned information among neural networks","volume":"91","author":"pratt","year":"0","journal-title":"Proc Assoc Adv Artif Intell Symp"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref37","article-title":"Phoneme recognition based on long temporal context","author":"schwarz","year":"2008"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref35","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref34","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815780"},{"key":"ref11","article-title":"Subspace regularized dynamic time warping for spoken query detection","author":"ram","year":"0","journal-title":"Proc Workshop Signal Process Adaptive Sparse Struct Representations"},{"key":"ref40","article-title":"Mediaeval 2013 spoken web search task: System performance measures","author":"r -fuentes","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1722"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.07.001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1973"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764270"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003752"},{"key":"ref19","first-page":"3690","article-title":"Sparse modeling of posterior exemplars for keyword detection","author":"ram","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref28","article-title":"The spoken web search task","author":"anguera","year":"0","journal-title":"Proc Mediaeval Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248714"},{"key":"ref6","first-page":"5838","article-title":"Coping with channel mismatch in query-by-example-but QUESST 2014","author":"sz\u00f6ke","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref5","first-page":"7819","article-title":"High-performance query-by-example spoken term detection on the SWS 2013 evaluation","author":"r -fuentes","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref1","article-title":"Language independent query by example spoken term detection","author":"ram","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1278"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462570"},{"key":"ref24","first-page":"237","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref23","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"0","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref41","article-title":"GTTS-EHU systems for QUESST at mediaeval 2014","author":"r -fuentes","year":"0","journal-title":"Proc MediaEval"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref25","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\/8938144\/09072650.pdf?arnumber=9072650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:23Z","timestamp":1651080683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9072650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2988788","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}