{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:30:17Z","timestamp":1757457017134,"version":"3.37.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/msp.2020.2969859","type":"journal-article","created":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T20:10:53Z","timestamp":1588363853000},"page":"39-49","source":"Crossref","is-referenced-by-count":24,"title":["Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition: A comparison of current training strategies"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4865-1307","authenticated-orcid":false,"given":"Xiaodong","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrich","family":"Finkler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Picheny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Kung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"0","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2700"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref12","first-page":"69","article-title":"The Fisher corpus: A resource for the next generation of speech-to-text","author":"cieri","year":"0","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref13","first-page":"161","article-title":"The tradeoffs of large scale learning","author":"bottou","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref15","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref16","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref17","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence o(1\/k2)","volume":"269","author":"nesterov","year":"1983","journal-title":"Soviet Math Dokl"},{"key":"ref18","article-title":"Highly scalable deep learning training system with mixed-precision: Training ImageNet in four minutes","author":"jia","year":"0","journal-title":"Proc Workshop on Systems for ML and Open Source Software in Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref28","first-page":"1058","article-title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs","author":"seide","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2912353"},{"key":"ref27","first-page":"3049","article-title":"Asynchronous decentralized parallel stochastic gradient descent","author":"lian","year":"0","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"ref29","first-page":"1710","article-title":"QSGD: Communication-ffficient SGD via gradient quantization and encoding","author":"alistarh","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854672"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682888"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"article-title":"Deep Speech: Scaling up end-to-end speech recognition","year":"2014","author":"hannun","key":"ref23"},{"key":"ref26","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/9084311\/09084348.pdf?arnumber=9084348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:35:53Z","timestamp":1651073753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9084348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/msp.2020.2969859","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"type":"print","value":"1053-5888"},{"type":"electronic","value":"1558-0792"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}