{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:45:06Z","timestamp":1780515906257,"version":"3.54.1"},"reference-count":51,"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":[{"DOI":"10.13039\/501100010218","name":"Department of Science and Technology","doi-asserted-by":"publisher","award":["ECR-01341\/2017"],"award-info":[{"award-number":["ECR-01341\/2017"]}],"id":[{"id":"10.13039\/501100010218","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Extra Mural","award":["EMR-2016\/007934"],"award-info":[{"award-number":["EMR-2016\/007934"]}]},{"DOI":"10.13039\/501100001502","name":"Department of Atomic Energy, Government of India","doi-asserted-by":"publisher","award":["DAE\/34\/20\/12\/2018-BRNS\/34088"],"award-info":[{"award-number":["DAE\/34\/20\/12\/2018-BRNS\/34088"]}],"id":[{"id":"10.13039\/501100001502","id-type":"DOI","asserted-by":"publisher"}]}],"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.2020.2983580","type":"journal-article","created":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T21:14:45Z","timestamp":1585775685000},"page":"1223-1232","source":"Crossref","is-referenced-by-count":17,"title":["Towards Relevance and Sequence Modeling in Language Recognition"],"prefix":"10.1109","volume":"28","author":[{"given":"Bharat","family":"Padi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5177-8291","authenticated-orcid":false,"given":"Anand","family":"Mohan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5779-9066","authenticated-orcid":false,"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178861"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2009.2019779"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991218"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683895"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854622"},{"key":"ref34","first-page":"237","author":"hochreiter","year":"2001","journal-title":"Gradient Flow in Recurrent Nets The Difficulty of Learning Long-term Dependencies"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.06.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2371"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00094-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.880085"},{"key":"ref20","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref26","first-page":"2930","article-title":"An investigation of deep neural network architectures for language recognition in indian languages.","author":"mounika","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004000"},{"key":"ref50","first-page":"1471","article-title":"Within-class covariance normalization for SVM-based speaker recognition","author":"hatch","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref51","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"arXiv 1510 08484 [cs]"},{"key":"ref10","first-page":"2041","article-title":"Phonotactic language recognition using MLP features","author":"benzeghiba","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2420092"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref12","first-page":"857","article-title":"Language recognition via i-vectors and dimensionality reduction","author":"dehak","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref16","first-page":"1846","article-title":"Robust language identification using convolutional neural network features","author":"ganapathy","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404779"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref4","first-page":"291","article-title":"The rats radio traffic collection system","author":"walker","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917992"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638990"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2237151"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.1996.481450"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-27"},{"key":"ref49","first-page":"216","article-title":"Description and analysis of the Brno system for LRE2011","author":"brummer","year":"0","journal-title":"Odyssey 2012 The Speaker and Language Recognition Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.943345"},{"key":"ref46","article-title":"Fant-filtering and noise adding tool","author":"hirsch","year":"2005"},{"key":"ref45","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref47","first-page":"1502","article-title":"TRAP Language identification system for RATS phase II evaluation","author":"han","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref41","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref43","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"0","journal-title":"NIPS 2014 Deep Learning Workshop"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09052484.pdf?arnumber=9052484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:20Z","timestamp":1651080680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2983580","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}