{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:35:47Z","timestamp":1725694547355},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053998","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7064-7068","source":"Crossref","is-referenced-by-count":3,"title":["Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings"],"prefix":"10.1109","author":[{"given":"Aku","family":"Rouhe","sequence":"first","affiliation":[{"name":"Aalto University,Department of Signal processing and acoustics"}]},{"given":"Tuomas","family":"Kaseva","sequence":"additional","affiliation":[{"name":"Aalto University,Department of Signal processing and acoustics"}]},{"given":"Mikko","family":"Kurimo","sequence":"additional","affiliation":[{"name":"Aalto University,Department of Signal processing and acoustics"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3935","article-title":"Enhancing the ted-lium corpus with selected data for language modeling and more ted talks","author":"rousseau","year":"2014","journal-title":"LREC"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref12","first-page":"1","article-title":"An analysis of incorporating an external language model into a sequence-tosequence model","author":"kannan","year":"2018","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a largescale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref17","article-title":"Evaluation of feature-space speaker adaptation for end-to-end acoustic models","author":"tomashenko","year":"2018","journal-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1423"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref28","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1438"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-460"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003979"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947358"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"article-title":"thin-resnet vlad pretrained models","year":"0","author":"xie","key":"ref26"},{"article-title":"x-vector and i-vector pretrained models download page","year":"0","author":"snyder","key":"ref25"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053998.pdf?arnumber=9053998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:57:48Z","timestamp":1659484668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053998","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}