{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:43:14Z","timestamp":1730230994049,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746459","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6872-6876","source":"Crossref","is-referenced-by-count":3,"title":["Phonotactic Language Recognition Using A Universal Phoneme Recognizer and A Transformer Architecture"],"prefix":"10.1109","author":[{"given":"David","family":"Romero","sequence":"first","affiliation":[{"name":"Universidad Politécnica Salesiana,Interaction, Robotics and Automation Research Group,Cuenca,Ecuador"}]},{"given":"Luis Fernando","family":"D'Haro","sequence":"additional","affiliation":[{"name":"Speech Technology and Machine Learning Group, Information and Telecommunication Center, Escuela é Superior de Ingenieros de Telecomunicación, Universidad Polit\u00e9cnica de Madrid, Ciudad Universitaria Avda. Complutense, 30, 28040, Madrid"}]},{"given":"Marcos","family":"Estecha-Garitagoitia","sequence":"additional","affiliation":[{"name":"Speech Technology Group, Information and Telecommunication Center, Universidad Polit\u00e9cnica de Madrid, Ciudad Universitaria Avda. Complutense, 30, 28040, Madrid"}]},{"given":"Christian","family":"Salamea","sequence":"additional","affiliation":[{"name":"Universidad Politécnica Salesiana,Interaction, Robotics and Automation Research Group,Cuenca,Ecuador"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2144","article-title":"Significance of neural phonotactic models for large-scale spoken language identification","author":"mojan","year":"2017","journal-title":"International Joint Conference on Neural Networks"},{"key":"ref11","first-page":"528","article-title":"The GTH-LID System for the Albayzin LRE12 Evaluation","author":"d\u2019haro","year":"2012","journal-title":"Iberspeech"},{"key":"ref12","article-title":"Language recognition in i-vectors space","author":"martinez","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219904"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.10.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2021-53"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref18","article-title":"Big Bird: Transformers for Longer Sequences","author":"zaheer","year":"2020","journal-title":"NIPS"},{"article-title":"Longformer: The longdocument transformer","year":"2020","author":"beltagy","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2018-12"},{"key":"ref27","article-title":"Extended Phone Log-Likelihood Ratio Features and Acoustic-Based iVectors por Language Recognition","author":"d'haro","year":"0","journal-title":"IEEE Intern Conf on Acoust Speech and Sig Proce ICASSP"},{"key":"ref3","article-title":"Phonotactic Language Recognition using i-vectors and Phoneme Posteriogram Counts","author":"d\u2019haro","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref6","article-title":"Incorporation of Language Discriminative Information into Recurrent Neural Networks Models to LID tasks","volume":"1154","author":"salamea","year":"2019","journal-title":"Smart Technologies Systems and Applications Communications in Computer and Information Science"},{"article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8395-7_25"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-17"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2018.8447373"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.1996.481450"},{"key":"ref9","article-title":"Phonotactic learning with neural language models","author":"mayer","year":"0","journal-title":"Proceedings of the Society for Computation in Linguistics"},{"key":"ref1","article-title":"Language Identification based on ngram Frequency Ranking","author":"cordoba","year":"2007","journal-title":"Eighth Annual Conference of the International Speech Communication Association"},{"key":"ref20","article-title":"Phoneme Recognition based on Long Temporal Context","author":"schwarz","year":"2009","journal-title":"PhD thesis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"article-title":"BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding","year":"2018","author":"devlin","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-015-9324-5"},{"key":"ref23","article-title":"Approaches to language identification using Gaussian mixture models and shifted delta cepstral features","author":"torres-carrasquillo","year":"2002","journal-title":"Seventh International Conference on Spoken Language Processing"},{"key":"ref26","article-title":"The 2009 NIST Language Recognition Evaluation","volume":"30","author":"martin","year":"2010","journal-title":"Speaker and Language Recognition Workshop"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"diederik","key":"ref25"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746459.pdf?arnumber=9746459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T15:46:15Z","timestamp":1663083975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746459","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}