{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T23:29:13Z","timestamp":1769729353113,"version":"3.49.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MOST","award":["110-2221-E-001 -002 -"],"award-info":[{"award-number":["110-2221-E-001 -002 -"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lsp.2022.3152672","type":"journal-article","created":{"date-parts":[[2022,2,18]],"date-time":"2022-02-18T20:26:35Z","timestamp":1645215995000},"page":"767-771","source":"Crossref","is-referenced-by-count":6,"title":["SVSNet: An End-to-End Speaker Voice Similarity Assessment Model"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6112-9380","authenticated-orcid":false,"given":"Cheng-Hung","family":"Hu","sequence":"first","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Huai","family":"Peng","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Chiyoda-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-689"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-211"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-210"},{"key":"ref13","article-title":"Robust phase-based speech signal processing from source-filter separation to model-based robust ASR","author":"Loweimi","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-14"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.3097493"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.3502473"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.3695401"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref24","volume-title":"Objective Measures of Speech Quality","author":"Quackenbush","year":"1986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref27","first-page":"6493","article-title":"DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Reddy","year":"2020"},{"key":"ref28","first-page":"482","article-title":"STOI-Net: A deep learning based non-intrusive speech intelligibility assessment model","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Zezario","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746688"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682676"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3059114"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053954"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2622"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref39","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref40","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462575"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2976193"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref46","first-page":"4797","article-title":"Conditional image generation with PixelCNN decoders","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Oord","year":"2016"},{"key":"ref47","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/13.1.25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyq191"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9686799\/09716822.pdf?arnumber=9716822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:42:11Z","timestamp":1705534931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9716822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/lsp.2022.3152672","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}