{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T14:17:49Z","timestamp":1771337869787,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003752","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"621-628","source":"Crossref","is-referenced-by-count":16,"title":["Multilingual Bottleneck Features for Query by Example Spoken Term Detection"],"prefix":"10.1109","author":[{"given":"Dhananjay","family":"Ram","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lesly","family":"Miculicich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herve","family":"Bourlard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"schwarz","year":"2008","journal-title":"Phoneme Recognition Based on Long Temporal Context"},{"key":"ref32","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref31","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref30","author":"jimmy","year":"2016","journal-title":"Layer normalization"},{"key":"ref35","article-title":"Mediaeval 2013 spoken web search task: system performance measures","author":"luis","year":"2013","journal-title":"n TR-2013-1 Department of Electricity and Electronics"},{"key":"ref34","article-title":"Speechdat (e)-eastern european telephone speech databases","author":"poll\u00e1k","year":"2000","journal-title":"Proc of XLDB 2000 Workshop on Very Large Telephone Speech Databases"},{"key":"ref10","first-page":"421","article-title":"Query-by-example spoken term detection using phonetic posteriorgram templates","author":"timothy","year":"2009","journal-title":"IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815780"},{"key":"ref13","article-title":"Subspace regularized dynamic time warping for spoken query detection","author":"ram","year":"2017","journal-title":"Workshop on Signal Processing with Adaptive Sparse Structured Representations (SPARS)"},{"key":"ref14","article-title":"Sparse modeling of posterior exemplars for keyword detection","author":"ram","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Re-ducing the dimensionality of data with neural networks","volume":"313","author":"geoffrey","year":"2006","journal-title":"Science"},{"key":"ref16","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref28","article-title":"An investigation of deep neural networks for multilingual speech recognition training and adaptation","author":"sibo","year":"2017","journal-title":"Proceedings of the Eighteenth Annual Conference of the International Speech Communication Association (IN-TERSPEECH)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1278"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"29","author":"geoffrey","year":"2012","journal-title":"Signal Processing Magazine"},{"key":"ref3","first-page":"7819","article-title":"High-performance query-by-example spoken term detection on the SWS 2013 evaluation","author":"javier","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179091"},{"key":"ref29","author":"paszke","year":"2017","journal-title":"Py-torch"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.07.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1722"},{"key":"ref7","first-page":"923","article-title":"Unsupervised bottleneck features for low-resource query-by-example spoken term detection","author":"chen","year":"2016","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248714"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref20","first-page":"4580","article-title":"Convolutional, long short-term memory, fully connected deep neural networks","author":"tara","year":"2015","journal-title":"2015 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref22","author":"xiong","year":"2016","journal-title":"Achieving human parity in conversational speech recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref26","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding IEEE Signal Processing Society"},{"key":"ref25","article-title":"Query by example search on speech at mediaeval 2014","author":"anguera","year":"2014","journal-title":"MediaEval"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003752.pdf?arnumber=9003752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:50:00Z","timestamp":1658155800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003752","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}