{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T21:09:42Z","timestamp":1779138582913,"version":"3.51.4"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.jvoice.2026.04.034","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T20:21:48Z","timestamp":1779135708000},"update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Dysphonic Artificial Intelligence Voice Cloning for Speech Intelligibility in Noise"],"prefix":"10.1016","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7394-4796","authenticated-orcid":false,"given":"Pasquale","family":"Bottalico","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3576-6770","authenticated-orcid":false,"given":"Charles J.","family":"Nudelman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2611-102X","authenticated-orcid":false,"given":"Daniel","family":"Fogerty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7508-6820","authenticated-orcid":false,"given":"Virginia","family":"Tardini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9638-7072","authenticated-orcid":false,"given":"Keiko","family":"Ishikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2026.04.034_bib1","first-page":"223","article-title":"Spasmodic dysphonia and vocal fold paralysis: outcomes of voice problems on work-related functioning","volume":"12","author":"Smith","year":"1998","journal-title":"J\u00a0Voice"},{"key":"10.1016\/j.jvoice.2026.04.034_bib2","unstructured":"International Organization for Standardization, Ergonomics \u2013 Assessment of Speech Communication; 2003."},{"key":"10.1016\/j.jvoice.2026.04.034_bib3","first-page":"953","article-title":"Speech recognition in adverse conditions:\u00a0a review","volume":"27","author":"Mattys","year":"2012","journal-title":"Lang\u00a0Cognit\u00a0Process"},{"key":"10.1016\/j.jvoice.2026.04.034_bib4","article-title":"The relationship between voice parameters and speech intelligibility: a scoping review","author":"Gao","year":"2024","journal-title":"J\u00a0Voice"},{"key":"10.1016\/j.jvoice.2026.04.034_bib5","first-page":"2912","article-title":"Intelligibility of dysphonic speech in auralized classrooms","volume":"150","author":"Bottalico","year":"2021","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2026.04.034_bib6","first-page":"561","article-title":"The impact of dysphonic voices on healthy listeners: listener reaction times, speech intelligibility, and listener comprehension","volume":"25","author":"Evitts","year":"2016","journal-title":"Am\u00a0J\u00a0Speech Lang\u00a0Pathol"},{"key":"10.1016\/j.jvoice.2026.04.034_bib7","first-page":"69","article-title":"Predicting intelligibility deficit in dysphonic speech with cepstral peak prominence","volume":"127","author":"Ishikawa","year":"2018","journal-title":"Ann\u00a0Otol\u00a0Rhinol\u00a0Laryngol"},{"key":"10.1016\/j.jvoice.2026.04.034_bib8","first-page":"659","article-title":"Perception and acoustic studies of vowel intelligibility in dysphonic speech","volume":"35","author":"Ishikawa","year":"2021","journal-title":"J\u00a0Voice"},{"key":"10.1016\/j.jvoice.2026.04.034_bib9","first-page":"322","article-title":"Systematic review of literature on speech intelligibility and classroom acoustics in elementary schools","volume":"54","author":"Murgia","year":"2023","journal-title":"Lang\u00a0Speech\u00a0Hear\u00a0Services\u00a0Schools"},{"key":"10.1016\/j.jvoice.2026.04.034_bib10","first-page":"430","article-title":"Estimation of quality and intelligibility of a speech signal with varying forms of additive noise","volume":"7","author":"Narayana","year":"2019","journal-title":"Int\u00a0J\u00a0Emerg\u00a0Trends\u00a0Eng\u00a0Res"},{"key":"10.1016\/j.jvoice.2026.04.034_bib11","doi-asserted-by":"crossref","unstructured":"Kempster GB, Gerratt\u00a0BR, Abbott KV, Barkmeier-Kraemer J, Hillman RE, Consensus auditory-perceptual evaluation of voice: development of a standardized clinical protocol; 2009.","DOI":"10.1037\/t71599-000"},{"key":"10.1016\/j.jvoice.2026.04.034_bib12","first-page":"305","article-title":"Evaluating voice quality","author":"Shrivastav","year":"2011","journal-title":"Handb\u00a0Voice Assess"},{"key":"10.1016\/j.jvoice.2026.04.034_bib13","first-page":"108","article-title":"Pattern recognition in muscle misuse voice disorders: How i do it","volume":"11","author":"Morrison","year":"1997","journal-title":"J\u00a0Voice"},{"key":"10.1016\/j.jvoice.2026.04.034_bib14","first-page":"4071","article-title":"Interactions between breathy and rough voice qualities and their contributions to overall dysphonia severity","volume":"65","author":"Park","year":"2022","journal-title":"J\u00a0Speech\u00a0Lang\u00a0Hear Res"},{"key":"10.1016\/j.jvoice.2026.04.034_bib15","first-page":"93","article-title":"Sinonasal and laryngeal sarcoidosis\u2014an uncommon presentation and management challenge","volume":"357","author":"Edriss","year":"2019","journal-title":"Am\u00a0J\u00a0Med\u00a0Sci"},{"key":"10.1016\/j.jvoice.2026.04.034_bib16","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/s00455-018-9956-x","article-title":"Amyloidosis of the upper aerodigestive tract: management of a rare disease and review of the literature","volume":"34","author":"Send","year":"2019","journal-title":"Dysphagia"},{"key":"10.1016\/j.jvoice.2026.04.034_bib17","first-page":"361","article-title":"Clinical aspects of spasmodic dysphonia","volume":"41","author":"Aminoff","year":"1978","journal-title":"J\u00a0Neurol\u00a0Neurosurg\u00a0Psychiatr"},{"key":"10.1016\/j.jvoice.2026.04.034_bib18","first-page":"21","article-title":"Speech intelligibility in severe adductor spasmodic dysphonia","volume":"47","author":"Bender","year":"2004","journal-title":"J\u00a0Speech\u00a0Lang\u00a0Hear\u00a0Res"},{"key":"10.1016\/j.jvoice.2026.04.034_bib19","volume":"1","author":"Goodfellow","year":"2016"},{"key":"10.1016\/j.jvoice.2026.04.034_bib20","doi-asserted-by":"crossref","unstructured":"Choi S, Han S, Kim D,\u00a0Ha S, Attentron: Few-shot text-to-speech utilizing attention-based variable-length embedding, arXiv preprint arXiv:2005.08484;\u00a02020.","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"10.1016\/j.jvoice.2026.04.034_bib21","doi-asserted-by":"crossref","unstructured":"Ada AA, J\u00f8rgensen SH, Fritsch J, Cultures of the ai paralinguistic in voice cloning tools. In: Companion Publication of the 2024 ACM Designing Interactive Systems Conference; 2024. pp.\u00a0249\u2013252.","DOI":"10.1145\/3656156.3663708"},{"key":"10.1016\/j.jvoice.2026.04.034_bib22","doi-asserted-by":"crossref","first-page":"820","DOI":"10.3390\/electronics12040820","article-title":"Zse-vits: a zero-shot expressive voice cloning method based on vits","volume":"12","author":"Li","year":"2023","journal-title":"Electronics"},{"key":"10.1016\/j.jvoice.2026.04.034_bib23","unstructured":"Betker J, Better speech synthesis through scaling, arXiv preprint arXiv:2305.07243; 2023."},{"key":"10.1016\/j.jvoice.2026.04.034_bib24","unstructured":"Eleven Labs, Eleven Labs Instant Voice Cloning, [Computer software];\u00a02024. \u3008https:\/\/shorturl.at\/ru2Wx\u3009."},{"key":"10.1016\/j.jvoice.2026.04.034_bib25","article-title":"People are poorly equipped to detect ai-powered voice clones","volume":"15","author":"Barrington","year":"2025","journal-title":"Sci\u00a0Rep"},{"key":"10.1016\/j.jvoice.2026.04.034_bib26","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3396377","article-title":"Zero-shot voice cloning text-to-speech for dysphonia disorder speakers","author":"Azizah","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.04.034_bib27","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1121\/1.408469","article-title":"Development of the hearing in noise test for the measurement of speech reception thresholds in quiet and in noise","volume":"95","author":"Nilsson","year":"1994","journal-title":"J\u00a0Acoust Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2026.04.034_bib28","unstructured":"Fairbanks G, Voice and articulation drillbook, (No Title); 1960."},{"key":"10.1016\/j.jvoice.2026.04.034_bib29","unstructured":"Etymotic Research Inc., QuickSIN Speech-in-Noise Test, Version 1.3; 2001."},{"key":"10.1016\/j.jvoice.2026.04.034_bib30","first-page":"1919","article-title":"The effect of background noise on intelligibility of dysphonic speech","volume":"60","author":"Ishikawa","year":"2017","journal-title":"J\u00a0Speech\u00a0Lang\u00a0Hear\u00a0Res"},{"key":"10.1016\/j.jvoice.2026.04.034_bib31","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B, Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia; 2010. pp. 1459\u20131462.","DOI":"10.1145\/1873951.1874246"},{"key":"10.1016\/j.jvoice.2026.04.034_bib32","first-page":"190","article-title":"The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing","volume":"7","author":"Eyben","year":"2015","journal-title":"IEEE Trans\u00a0Affective Comput"},{"key":"10.1016\/j.jvoice.2026.04.034_bib33","doi-asserted-by":"crossref","unstructured":"Xue W, Cucchiarini C, van Hout R, Strik H, Acoustic correlates of speech intelligibility. The usability of the egemaps feature set for atypical speech. In:\u00a0Proceedings of SLaTE 2019; 2019.","DOI":"10.21437\/SLaTE.2019-9"},{"key":"10.1016\/j.jvoice.2026.04.034_bib34","unstructured":"R Core Team, R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria;\u00a02021. \u3008https:\/\/www.R-project.org\/\u3009."},{"key":"10.1016\/j.jvoice.2026.04.034_bib35","doi-asserted-by":"crossref","unstructured":"Hastie\u00a0T, Tibshirani R, Friedman J. An introduction to statistical learning;\u00a02009.","DOI":"10.1007\/978-0-387-84858-7_1"},{"key":"10.1016\/j.jvoice.2026.04.034_bib36","series-title":"IT Convergence and Security 2017","first-page":"112","article-title":"A comparison of model validation techniques for audio-visual speech recognition","author":"Seong","year":"2018"},{"key":"10.1016\/j.jvoice.2026.04.034_bib37","first-page":"137","article-title":"Calculation of signal detection theory measures","volume":"31","author":"Stanislaw","year":"1999","journal-title":"Behav\u00a0Res\u00a0Method\u00a0Instruments\u00a0Comput"},{"key":"10.1016\/j.jvoice.2026.04.034_bib38","first-page":"381","article-title":"Primacy versus recency in persuasion as a function of the timing of arguments and measures","volume":"69","author":"Insko","year":"1964","journal-title":"J\u00a0Abnormal\u00a0Soc\u00a0Psychol"},{"key":"10.1016\/j.jvoice.2026.04.034_bib39","doi-asserted-by":"crossref","unstructured":"M\u00fcller NM, Pizzi K, Williams J. Human perception of audio deepfakes. In: Proceedings of the 1st international workshop on deepfake detection for audio multimedia; 2022. pp. 85\u201391.","DOI":"10.1145\/3552466.3556531"},{"key":"10.1016\/j.jvoice.2026.04.034_bib40","first-page":"e223","article-title":"Spectral-and cepstral-based measures during continuous speech: capacity to distinguish dysphonia and consistency within a speaker","volume":"25","author":"Lowell","year":"2011","journal-title":"J\u00a0Voice"},{"key":"10.1016\/j.jvoice.2026.04.034_bib41","first-page":"2457","article-title":"Syllabic strength and lexical boundary decisions in the perception of hypokinetic dysarthric speech","volume":"104","author":"Liss","year":"1998","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2026.04.034_bib42","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.neuroimage.2015.06.087","article-title":"Effects of language experience and stimulus context on the neural organization and categorical perception of speech","volume":"120","author":"Bidelman","year":"2015","journal-title":"Neuroimage"},{"key":"10.1016\/j.jvoice.2026.04.034_bib43","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0285333","article-title":"Warning: humans cannot reliably detect speech deepfakes","volume":"18","author":"Mai","year":"2023","journal-title":"PloS One"},{"key":"10.1016\/j.jvoice.2026.04.034_bib44","first-page":"13","article-title":"Intelligibility related to loudness","volume":"13","author":"Moore","year":"1946","journal-title":"Commun\u00a0Monogr"},{"key":"10.1016\/j.jvoice.2026.04.034_bib45","first-page":"781","article-title":"Perception of emotion in conversational speech by younger and older listeners","volume":"7","author":"Schmidt","year":"2016","journal-title":"Front\u00a0Psychol"},{"key":"10.1016\/j.jvoice.2026.04.034_bib46","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/S0167-6393(96)00063-5","article-title":"Intelligibility of normal speech i: Global and fine-grained acoustic-phonetic talker characteristics","volume":"20","author":"Bradlow","year":"1996","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.04.034_bib47","series-title":"Encyclopedia of Cyber Behavior","first-page":"212","article-title":"Digital natives","author":"Bennett","year":"2012"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199726002055?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199726002055?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T20:21:57Z","timestamp":1779135717000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199726002055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":47,"alternative-id":["S0892199726002055"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.04.034","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Exploring Dysphonic Artificial Intelligence Voice Cloning for Speech Intelligibility in Noise","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.04.034","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc. on behalf of The Voice Foundation.","name":"copyright","label":"Copyright"}]}}