{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:19:47Z","timestamp":1777130387322,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639650","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"105-111","source":"Crossref","is-referenced-by-count":8,"title":["Unsupervised Representation Learning of Speech for Dialect Identification"],"prefix":"10.1109","author":[{"given":"Suwon","family":"Shon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","year":"0","journal-title":"The NIST 2015 Language Recognition Evaluation Plan"},{"key":"ref32","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU.2017.8268958","article-title":"UTD-CRSS Submission for MGB-3 Arabic Dialect Identification: Front-end and Back-end Advancements on Broadcast Speech","author":"bulut","year":"2017","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461486"},{"key":"ref11","first-page":"1","article-title":"Language Identification and Morphosyntactic Tagging: The Second VarDial Evaluation Campaign","author":"zampieri","year":"2018","journal-title":"Proc of the Fifth Workshop on NLP for Similar Languages Varieties and Dialects"},{"key":"ref12","first-page":"98","article-title":"Convolutional neural network and language embeddings for end-to-end dialect recognition","author":"shon","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854353"},{"key":"ref14","first-page":"260","article-title":"Unsupervised Domain Adaptation for I-Vector Speaker Recognition","author":"garcia-romero","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref15","first-page":"265","article-title":"Unsupervised Clustering Approaches for Domain Adaptation in Speaker Recognition Systems","author":"shum","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.21437\/Interspeech.2017-49","article-title":"Autoencoder based Domain Adaptation for Speaker Recognition under Insufficient Channel Information","author":"shon","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2797420"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"2576","DOI":"10.21437\/Interspeech.2017-576","article-title":"Dialect recognition based on unsupervised bottleneck features","author":"zhang","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462037"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2571","DOI":"10.21437\/Interspeech.2017-44","article-title":"End-to-end language identification using high-order utterance representation with bilinear pooling","author":"jin","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.21437\/Interspeech.2017-349","article-title":"Learning latent representations for speech generation and transformation","author":"hsu","year":"2017","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"857","DOI":"10.21437\/Interspeech.2011-328","article-title":"Language recognition via Ivectors and dimensionality reduction","author":"dehak","year":"2011","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagraniy","year":"2017","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268952"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"109","DOI":"10.21437\/Odyssey.2016-16","article-title":"Deep Language: a comprehensive deep learning approach to end-to-end language recognition","author":"trong","year":"2016","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1297"},{"key":"ref7","first-page":"165","article-title":"Deep Neural Network Embeddings for Text-Independent Speaker Verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref2","first-page":"1146","article-title":"A Unified Deep Neural Network for Speaker and Language Recognition","author":"richardson","year":"2015","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1391"},{"key":"ref1","first-page":"2867","article-title":"Speaker adaptation using the i-vector technique for bottleneck features","author":"cardinal","year":"2015","journal-title":"InterSpeech"},{"key":"ref20","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"299","DOI":"10.21437\/Odyssey.2014-45","article-title":"Neural Network Bottleneck Features for Language Identification","author":"matejka","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref21","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268960"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853583"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639622"},{"key":"ref25","first-page":"105","article-title":"Spoken language recognition using x-vectors","author":"snyder","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639650.pdf?arnumber=8639650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T20:14:28Z","timestamp":1720988068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639650","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}