{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:26:23Z","timestamp":1760955983466,"version":"3.37.3"},"reference-count":66,"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":"am","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":"NSF","award":["1619212","1623750"],"award-info":[{"award-number":["1619212","1623750"]}]}],"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.2019.2955289","type":"journal-article","created":{"date-parts":[[2019,11,22]],"date-time":"2019-11-22T21:18:50Z","timestamp":1574457530000},"page":"343-354","source":"Crossref","is-referenced-by-count":9,"title":["Learning Structured Sparse Representations for Voice Conversion"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2108-3111","authenticated-orcid":false,"given":"Shaojin","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6059-4053","authenticated-orcid":false,"given":"Guanlong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5871-0596","authenticated-orcid":false,"given":"Christopher","family":"Liberatore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricardo","family":"Gutierrez-Osuna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"543","article-title":"Tree-guided group lasso for multi-task regression with structured sparsity","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553431"},{"key":"ref33","first-page":"608","article-title":"SABR: sparse, anchor-based representation of the speech signal","author":"liberatore","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","first-page":"677","article-title":"Sparse representation of phonetic features for voice conversion with and without parallel data","author":"cicman","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-227"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2644258"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-567"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462589"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref63","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","author":"berndt","year":"0","journal-title":"Proc Int Conf Knowl Discovery Data Mining"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541114"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038818"},{"key":"ref66","first-page":"3053","article-title":"Crowdsourcing preference tests, and how to detect cheating","author":"buchholz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953213"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref20","article-title":"Voice conversion with smoothed GMM and MAP adaptation","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref26","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178902"},{"key":"ref51","first-page":"1502","article-title":"Viterbi training for PCFGs: Hardness results and competitiveness of uniform initialization","author":"cohen","year":"0","journal-title":"Proc Meeting Assoc Comput Linguist"},{"key":"ref59","first-page":"283","article-title":"Generalized nonnegative matrix approximations with Bregman divergences","author":"sra","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","author":"efron","year":"2004","journal-title":"Ann Statist"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.52"},{"key":"ref54","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"0","journal-title":"Proc Berkeley Symp Math Statist Probability Vol 1 Statist"},{"journal-title":"Information Theory Inference and Learning Algorithms","year":"2003","author":"mackay","key":"ref53"},{"key":"ref52","first-page":"688","article-title":"Unified expectation maximization","author":"samdani","year":"0","journal-title":"Proc Conf North Am Chapter Assoc Comput Linguist Human Lang Technol"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOS584"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2180-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855137"},{"key":"ref14","first-page":"3077","article-title":"Foreign accent conversion through voice morphing","author":"aryal","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1272"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1295"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143880"},{"key":"ref19","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"0","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694344"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1437"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637625"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2833258.2833276"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.09.004"},{"key":"ref48","first-page":"2138","article-title":"Group sparsity for speaker identity discrimination in factorisation-based speech recognition","author":"hurmalainen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336927"},{"key":"ref42","first-page":"487","article-title":"Proximal methods for sparse hierarchical dictionary learning","author":"jenatton","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","first-page":"82","article-title":"Group sparse coding","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-016-2764-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995712"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/8938144\/8910392-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08910392.pdf?arnumber=8910392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:23Z","timestamp":1651080683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8910392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2955289","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}