{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:48:07Z","timestamp":1778255287222,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3231714","type":"journal-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T18:35:30Z","timestamp":1672857330000},"page":"633-642","source":"Crossref","is-referenced-by-count":18,"title":["Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7533-2630","authenticated-orcid":false,"given":"Jun","family":"Qi","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, School of Information Science and Engineering, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2879-8811","authenticated-orcid":false,"given":"Chao-Han Huck","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1039-8369","authenticated-orcid":false,"given":"Pin-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Height, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7699-5620","authenticated-orcid":false,"given":"Javier","family":"Tejedor","sequence":"additional","affiliation":[{"name":"Institute of Technology, Universidad San Pablo-CEU, CEU Universities, Urbanización Montepríncipe, Boadilla del Monte, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Automatic Speech Recognition: A Deep Learning Approach, Signals and Communication Technology","author":"Yu","year":"2016"},{"key":"ref2","first-page":"1","article-title":"Towards understanding the role of over-parametrization in generalization of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Neyshabur","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2993164"},{"key":"ref5","article-title":"Theoretical error performance analysis for deep neural network based regression functional approximation","author":"Qi","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Representation Learn.","author":"Liu","year":"2019"},{"key":"ref8","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","volume-title":"Proc. Int. Conf. Representation Learn.","author":"Zhu","year":"2017"},{"key":"ref9","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Malach","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2690524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383405"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2010.06.030"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7439(02)00089-8"},{"key":"ref16","first-page":"442","article-title":"Tensorizing neural networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Novikov","year":"2015"},{"key":"ref17","first-page":"7504","article-title":"Tensor-train network-based tensor-to-vector regression for multi-channel speech enhancement","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Qi","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1900"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747327"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747636"},{"key":"ref22","volume-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2013.6571843"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2254619"},{"key":"ref25","article-title":"Ultimate tensorization: Compressing convolutional and FC layers alike","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Garipov","year":"2016"},{"key":"ref26","first-page":"3891","article-title":"Tensor-train recurrent neural networks for video classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2017"},{"key":"ref27","article-title":"Long-term forecasting using tensor-train RNNs","author":"Yu","year":"2017"},{"key":"ref28","first-page":"726","article-title":"Scalable Gaussian processes with billions of inducing inputs via tensor-train decomposition","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Izmailov","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3051490"},{"key":"ref30","first-page":"441","article-title":"Tensor decompositions in deep learning","volume-title":"Proc. 28th Eur. Symp. Artif. Neural Netw., Comput. Intell. Mach. Learn.","author":"Bacciu","year":"2020"},{"key":"ref31","article-title":"Introduction to tensor decompositions and their applications in machine learning","author":"Rabanser","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.aop.2014.06.013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.99.120601"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.78.205116"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref36","first-page":"4592","article-title":"Riemannian SVRG: Fast stochastic optimization on riemannian manifolds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Zhang","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-487"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163353"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-7-1247-2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3016837"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3800(89)90035-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3354\/cr030079"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref47","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref48","first-page":"2488","article-title":"How does batch normalization help optimization?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Santurkar","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.317"},{"key":"ref50","first-page":"8792","article-title":"Generalized cross-entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11284"},{"key":"ref52","article-title":"A neural attention model for speech command recognition","author":"Andrade","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413453"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10006412.pdf?arnumber=10006412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T05:23:18Z","timestamp":1707456198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10006412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3231714","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}