{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:07Z","timestamp":1740172447225,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFB1002202"],"award-info":[{"award-number":["2017YFB1002202"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61671422","U1613211"],"award-info":[{"award-number":["61671422","U1613211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Science and Technology Project of Anhui Province","award":["17030901005"],"award-info":[{"award-number":["17030901005"]}]},{"name":"Huawei Noah's Ark Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2980372","type":"journal-article","created":{"date-parts":[[2020,3,12]],"date-time":"2020-03-12T20:45:03Z","timestamp":1584045903000},"page":"1025-1037","source":"Crossref","is-referenced-by-count":2,"title":["Online Speaker Adaptation Using Memory-Aware Networks for Speech Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-1744","authenticated-orcid":false,"given":"Jia","family":"Pan","sequence":"first","affiliation":[]},{"given":"Genshun","family":"Wan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3207-2258","authenticated-orcid":false,"given":"Zhongfu","family":"Ye","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659609"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178784"},{"key":"ref33","first-page":"343","article-title":"Domain separation networks","author":"bousmalis","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref32","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume":"37","author":"ganin","year":"0","journal-title":"Proc JMLR Workshop Conf Proc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178787"},{"key":"ref37","first-page":"214","article-title":"Unsupervised adaptation with domain separation networks for robust speech recognition","author":"meng","year":"0","journal-title":"Proc IEEE Autom Speech Recognition Understanding"},{"key":"ref36","first-page":"132","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461682"},{"key":"ref60","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref28","first-page":"122","article-title":"Embedding-based speaker adaptive training of deep neural networks","author":"cui","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TASLP.2014.2346313","article-title":"Fast adaptation of deep neural network based on discriminant codes for speech recognition","volume":"22","author":"xue","year":"2014","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461553"},{"key":"ref2","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref21","first-page":"2180","article-title":"Adaptation of deep neural network acoustic models using factorised i-vectors","author":"karanasou","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"2867","article-title":"Speaker adaptation using the i-vector technique for bottleneck features","author":"cardinal","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854824"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref50","first-page":"3942","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"perez","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115546"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref54"},{"article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","year":"2018","author":"du","key":"ref53"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682667"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472633"},{"key":"ref40","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","author":"macqueen","year":"0","journal-title":"Proc 5th Berkeley Symp Math Statist Probability"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953086"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2601146"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462112"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref18","first-page":"3625","article-title":"Rapid adaptation for deep neural networks through multi-task learning","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref5","first-page":"2171","article-title":"Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system","author":"neto","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref7","first-page":"526","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref45","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref43","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09034033.pdf?arnumber=9034033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:30:50Z","timestamp":1651080650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9034033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2980372","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}