{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:31:47Z","timestamp":1776882707874,"version":"3.51.2"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639622","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T18:36:34Z","timestamp":1550169394000},"page":"1007-1013","source":"Crossref","is-referenced-by-count":41,"title":["Frame-Level Speaker Embeddings for Text-Independent Speaker Recognition and Analysis of End-to-End Model"],"prefix":"10.1109","author":[{"given":"Suwon","family":"Shon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462575"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853583"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163903"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref15","article-title":"Fine-grained analysis of sentence embeddings using auxiliary prediction tasks","author":"adi","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref16","first-page":"2438","article-title":"Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems","author":"belinkov","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"133","article-title":"A quantitative assessment of the relative speaker discriminating properties of phoenems","volume":"1","author":"eatock","year":"1994","journal-title":"IEEE ICASSP"},{"key":"ref18","first-page":"49","article-title":"Broad Phonetic Classes Expressing Speaker","volume":"li","author":"antal","year":"2006","journal-title":"Knowledge Creation Diffusion Utilization"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.21437\/Interspeech.2017-1125","article-title":"What does the speaker embedding encode?","volume":"2017 augus","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref3","first-page":"999","article-title":"Deep Neural Network Embeddings for Text-Independent Speaker Verification","author":"snyder","year":"0"},{"key":"ref6","first-page":"217","article-title":"On autoencoders in the i - vector space for speaker recognition","author":"pekhovsky","year":"2016","journal-title":"Odyssey 2016 The Speaker and Language Recognition Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853888"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2420092"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2752462"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2016.7846309","article-title":"End-to-end training approaches for discriminative segmental models","author":"tang","year":"2016","journal-title":"IEEE Workshop on Spoken Language Technology (SLT)"},{"key":"ref21","article-title":"Sequence Prediction with Neural Segmental Models","author":"tang","year":"2017","journal-title":"Ph D thesis"}],"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\/08639622.pdf?arnumber=8639622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T01:52:35Z","timestamp":1643248355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639622","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}