{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:23Z","timestamp":1760245043682,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61371136","61633013"],"award-info":[{"award-number":["61371136","61633013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Basic Research Program (973 Program) of China","award":["2013CB329302"],"award-info":[{"award-number":["2013CB329302"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1109\/taslp.2017.2764271","type":"journal-article","created":{"date-parts":[[2017,10,18]],"date-time":"2017-10-18T18:26:52Z","timestamp":1508351212000},"page":"134-144","source":"Crossref","is-referenced-by-count":44,"title":["Phonetic Temporal Neural Model for Language Identification"],"prefix":"10.1109","volume":"26","author":[{"given":"Zhiyuan","family":"Tang","sequence":"first","affiliation":[]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yixiang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Lantian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Abel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415532"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-180"},{"key":"ref32","first-page":"2155","article-title":"Automatic language identification using long short-term memory recurrent neural networks","author":"gonzalez-dominguez","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1334"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/978-3-319-43958-7_53","article-title":"Language identification using time delay neural network d-vector on short utterances","volume":"9811","author":"kotov","year":"2016","journal-title":"Int Conf on Speech and Computers"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-13"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2496226"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1049\/el.2013.1721"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0146917"},{"key":"ref10","first-page":"89","article-title":"Approaches to language identification using Gaussian mixture models and shifted delta cepstral features","author":"torres-carrasquillo","year":"2002","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319323"},{"key":"ref12","first-page":"74","article-title":"Comparing Gaussian mixture and neural network modelling approaches to automatic language identification of speech","author":"willmore","year":"2000","journal-title":"Proc Australian Int Conf Speech Sci Technol"},{"key":"ref13","first-page":"1633","article-title":"Automatic language identification using discrete hidden Markov model","author":"wong","year":"2004","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref14","first-page":"1011","article-title":"Speaker-independent, text-independent language identification by HMM","volume":"92","author":"nakagawa","year":"1992","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref15","first-page":"909","article-title":"Identifying language from speech: An example of high-level, statistically-based feature extraction","author":"kwasny","year":"1992","journal-title":"Proc 7th Annu Conf Cogn Sci Soc"},{"article-title":"A segmental approach to automatic language identification","year":"1993","author":"muthusamy","key":"ref16"},{"key":"ref17","first-page":"41","article-title":"Language recognition with support vector machines","author":"campbell","year":"2004","journal-title":"Proc Odyssey"},{"key":"ref18","first-page":"857","article-title":"Language recognition via i-vectors and dimensionality reduction","author":"dehak","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref19","first-page":"861","article-title":"Language recognition in iVectors space","author":"mart?nez","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref28","first-page":"403","article-title":"An end-to-end approach to language identification in short utterances using convolutional neural networks","author":"lozano-diez","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_40"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854622"},{"journal-title":"The Cambridge Encyclopedia of Language","year":"2010","author":"crystal","key":"ref3"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"391","DOI":"10.21437\/Eurospeech.1999-101","article-title":"Human language identification with reduced spectral information","author":"mori","year":"1999","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-30"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389288"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.943345"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.4324\/9780203301524","author":"comrie","year":"2009","journal-title":"The World s Major Languages"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1168879"},{"journal-title":"An Introduction to Language","year":"2010","author":"fromkin","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.1996.481450"},{"key":"ref45","article-title":"Hierarchical multiscale recurrent neural networks","author":"chung","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.418211"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248093"},{"key":"ref42","article-title":"Parallel training of deep neural networks with natural gradient and parameter averaging","author":"povey","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543237"},{"key":"ref41","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref23","first-page":"2833","article-title":"Different size multilingual phone inventories and context-dependent acoustic models for language identification","author":"zhu","year":"2005","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref44","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref26","first-page":"40","article-title":"Modeling prosody for language identification on read and spontaneous speech","volume":"6","author":"rouas","year":"2003","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-17"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596136"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8124117\/08070977.pdf?arnumber=8070977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T20:57:37Z","timestamp":1659646657000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8070977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2764271","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}