{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:40:44Z","timestamp":1773621644014,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688017","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"1102-1109","source":"Crossref","is-referenced-by-count":7,"title":["SpeechNAS: Towards Better Trade-Off Between Latency and Accuracy for Large-Scale Speaker Verification"],"prefix":"10.1109","author":[{"given":"Wentao","family":"Zhu","sequence":"first","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlong","family":"Kong","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shun","family":"Lu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixiang","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Deng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref38","article-title":"Darts: Differentiable architecture search","author":"liu","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1258"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004029"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003935"},{"key":"ref30","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 Transactions on Audio Speech and Language Processing"},{"key":"ref37","first-page":"544","article-title":"Single path one-shot neural architecture search with uniform sampling","author":"guo","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref36","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"cai","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref35","article-title":"Efficienttdnn: Efficient architecture search for speaker recognition in the wild","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3057"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.201"},{"key":"ref27","article-title":"Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks","volume":"30","author":"zhu","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003938"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003860"},{"key":"ref22","article-title":"Res2net: A new multi-scale backbone architecture","author":"gao","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003794"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004023"},{"key":"ref50","author":"barras","year":"2012","journal-title":"SoX Sound eXchange"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467061"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683097"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682749"},{"key":"ref17","first-page":"6225","article-title":"Learning towards minimum hyper-spherical energy","author":"liu","year":"0","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003995"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2713"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2357"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704310024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1058"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1769"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref45","first-page":"2616","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc Interspeech 2017"},{"key":"ref48","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref47","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2031"},{"key":"ref41","first-page":"937","article-title":"Bayesian optimization with inequality constraints","volume":"2014","author":"gardner","year":"0","journal-title":"ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1626"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688017.pdf?arnumber=9688017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:39Z","timestamp":1652733699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688017","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}