{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T18:10:27Z","timestamp":1760638227096,"version":"build-2065373602"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"\u201cDARE\u2013Digital Lifelong Prevention\u201d Project","award":["PNC0000002","CUP: B53C22006450001"],"award-info":[{"award-number":["PNC0000002","CUP: B53C22006450001"]}]},{"name":"Italian Complementary National Plan PNC-I.1 Research Initiatives for Innovative Technologies and Pathways in the Health and Welfare Sector","award":["D.D. 931 of 06\/06\/2022"],"award-info":[{"award-number":["D.D. 931 of 06\/06\/2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3619782","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:54:48Z","timestamp":1760032488000},"page":"175718-175732","source":"Crossref","is-referenced-by-count":0,"title":["Foundation Models for Speech Enhancement Leveraging Consistency Constraints and Contrast Stretching"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7801-798X","authenticated-orcid":false,"given":"Muhammad","family":"Salman Khan","sequence":"first","affiliation":[{"name":"University of Enna &#x201C;Kore,&#x201D;, Enna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1048-7380","authenticated-orcid":false,"given":"Valerio","family":"Mario Salerno","sequence":"additional","affiliation":[{"name":"University of Enna &#x201C;Kore,&#x201D;, Enna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8838-064X","authenticated-orcid":false,"given":"Moreno","family":"la Quatra","sequence":"additional","affiliation":[{"name":"University of Enna &#x201C;Kore,&#x201D;, Enna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuo-Hsuan","family":"Hung","sequence":"additional","affiliation":[{"name":"Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"Nvidia Corporation, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0770-0507","authenticated-orcid":false,"given":"Sabato","family":"Marco Siniscalchi","sequence":"additional","affiliation":[{"name":"University of Palermo, Palermo, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470994443"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"volume-title":"Spoken Language Processing","year":"2001","author":"Huang","key":"ref3"},{"volume-title":"Speech Enhancement","year":"2005","author":"Benesty","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414346"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10714933"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3017042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3366760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383624"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10727"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-302"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1864"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163086"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2024.3378602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref29","first-page":"436","article-title":"Deep learning","volume":"2015","author":"LeCun","year":"2006","journal-title":"Nature"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854299"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3050386"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref39","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. ICML","author":"Fu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-456"},{"key":"ref43","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. NeurIPS","author":"Goodfellow"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2291"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref47","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3505794"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888830"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref55","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref58","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625960"},{"key":"ref61","first-page":"125","article-title":"HEAR: Holistic evaluation of audio representations","volume-title":"Proc. NeurIPS Competitions Demonstrations Track","author":"Turian"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-022-00772-5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.12928\/telkomnika.v21i1.24261"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890672"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1917\/1\/012009"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-486"},{"key":"ref67","first-page":"15147","article-title":"Speech analysis of language varieties in Italy","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics","author":"Quatra"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-957"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1980"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023356"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447220"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref78","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chiu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"issue":"4","key":"ref80","first-page":"1","article-title":"Conformer-based sound event detection with semi-supervised learning and data augmentation","volume":"1","author":"Miyazaki","year":"2020","journal-title":"Dim"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413555"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP61759.2024.10743615"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10478"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447573"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref90","article-title":"Phase-aware speech enhancement with deep complex U-Net","author":"Choi","year":"2019","journal-title":"arXiv:1903.03107"},{"volume-title":"American National Standard: Methods for Calculation of the Speech Intelligibility Index","year":"1997","key":"ref91"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref94","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"arXiv:1412.6980"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-565"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831254"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095666"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-582"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-339"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3284522"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313442"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271151"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747647"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11197472.pdf?arnumber=11197472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:39:13Z","timestamp":1760636353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":111,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3619782","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}