{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:57:41Z","timestamp":1762325861296,"version":"build-2065373602"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1109\/taslp.2024.3369536","type":"journal-article","created":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T19:10:02Z","timestamp":1708715402000},"page":"1736-1749","source":"Crossref","is-referenced-by-count":4,"title":["Time-Domain Speech Super-Resolution With GAN Based Modeling for Telephony Speaker Verification"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6311-2155","authenticated-orcid":false,"given":"Saurabh","family":"Kataria","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-8426","authenticated-orcid":false,"given":"Jes\u00fas","family":"Villalba","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3033-7005","authenticated-orcid":false,"given":"Laureano","family":"Moro-Vel\u00e1zquez","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8245-0413","authenticated-orcid":false,"given":"Piotr","family":"\u017belasko","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-5753","authenticated-orcid":false,"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"article-title":"A survey on neural speech synthesis","year":"2021","author":"Tan","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2012-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2713"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2020-66"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3130975"},{"key":"ref9","first-page":"1133","article-title":"A unified deep speaker embedding framework for mixed-bandwidth speech data","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Cai","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10900"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2589"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2394"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-555"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00587"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.4903917"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref23","article-title":"Bayesian speaker verification with heavy-tailed priors","volume-title":"Proc. Speaker Lang. Recognit. Workshop (Odyssey 2010)","author":"Kenny","year":"2010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170672"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854773"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462547"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2003.1198872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178801"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3043"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1941"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2605"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747699"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682367"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413555"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1502"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706575"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413575"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682760"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190726"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1508"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682992"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-63"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937169"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"article-title":"Conditional generative adversarial nets","year":"2014","author":"Mirza","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10985"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10977"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref52","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref53","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"article-title":"Geometric GAN","year":"2017","author":"Lim","key":"ref57"},{"key":"ref58","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky","year":"2017"},{"key":"ref59","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gulrajani","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00666"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"issue":"11","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"article-title":"NIST 2021 speaker recognition evaluation plan","year":"2021","author":"Sadjadi","key":"ref64"},{"article-title":"The 2016 NIST speaker recognition evaluation","volume-title":"Interspeech","author":"Seyed","key":"ref65"},{"article-title":"The JHU-MIT system description for NIST SRE20 CTS challenge","year":"2022","author":"Villalba","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-30"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2020-39"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2022-49"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206817"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-47"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10444048.pdf?arnumber=10444048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T18:57:10Z","timestamp":1709924230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3369536","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}