{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:35Z","timestamp":1760245055001,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683185","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T16:07:22Z","timestamp":1555430842000},"page":"6211-6215","source":"Crossref","is-referenced-by-count":22,"title":["Speaker Characterization Using TDNN-LSTM Based Speaker Embedding"],"prefix":"10.1109","author":[{"given":"Chia-Ping","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Su-Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Ting","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tenghui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chien-Lin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A Time Delay Neural Network Architecture for Efficient Modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-133","article-title":"Speaker Characterization Using Long-Term and Temporal Information","author":"huang","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-348","article-title":"Ensemble Classifiers Using Unsupervised Data Selection for Speaker Recognition","author":"huang","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2018-15","article-title":"Spoken Language Recognition using X-vectors","author":"snyder","year":"2018","journal-title":"Proc Odyssey"},{"article-title":"Musan: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref15"},{"key":"ref16","article-title":"Audio Augmentation for Speech Recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"year":"0","key":"ref17"},{"key":"ref18","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"year":"2018","key":"ref19","article-title":"NIST 2018 Speaker Recognition Evaluation Plan"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TIFS.2017.2678458","article-title":"Speaker Identification Using Discriminative Features and Sparse Representation","volume":"12","author":"wang","year":"2017","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep Neural Network Embeddings for Text-independent Speaker Verification","author":"snyder","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-End Factor Analysis For Speaker Verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Trans Audio Speech and Language Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"year":"2016","key":"ref20","article-title":"NIST 2016 Speaker Recognition Evaluation Plan"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683185.pdf?arnumber=8683185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T22:54:03Z","timestamp":1663282443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683185","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}