{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T16:52:34Z","timestamp":1794070354691,"version":"4.8.0"},"reference-count":27,"publisher":"Pacini Editore","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Acta Otorhinolaryngol Ital"],"DOI":"10.14639\/0392-100x-n2309","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T07:15:13Z","timestamp":1690787713000},"page":"317-323","source":"Crossref","is-referenced-by-count":10,"title":["Artificial intelligence for the recognition of benign lesions of vocal folds from audio recordings","Il ruolo del machine learning nel riconoscimento delle lesioni cordali benigne dal segnale vocale"],"prefix":"10.14639","volume":"43","author":[{"given":"Maria Raffaella","family":"Marchese","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Sensoli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvia","family":"Campagnini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Cianchetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Nacci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Ursino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucia","family":"D\u2019Alatri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacopo","family":"Galli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Chiara","family":"Carrozza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaetano","family":"Paludetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Mannini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"20340","published-online":{"date-parts":[[2023,10]]},"reference":[{"key":"10.14639\/0392-100X-N2309_ref1","doi-asserted-by":"crossref","unstructured":"Robin J, Harrison JE, Kaufman LD, et al. Evaluation of speech-based digital biomarkers: review and recommendations. Digit Biomark 2020;4:99-108. https:\/\/doi.org\/10.1159\/000510820","DOI":"10.1159\/000510820"},{"key":"10.14639\/0392-100X-N2309_ref2","doi-asserted-by":"crossref","unstructured":"Li M, Han KJ, Narayanan S. Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Comput Speech Lang 2013;27:151-167. https:\/\/doi.org\/10.1016\/j.csl.2012.01.008","DOI":"10.1016\/j.csl.2012.01.008"},{"key":"10.14639\/0392-100X-N2309_ref3","doi-asserted-by":"crossref","unstructured":"Berardi ML, Hunter EJ, Ferguson SH. Talker age estimation using machine learning. Proc Meet Acoust 2017;30:040014. https:\/\/doi.org\/10.1121\/2.0000921","DOI":"10.1121\/2.0000921"},{"key":"10.14639\/0392-100X-N2309_ref4","doi-asserted-by":"crossref","unstructured":"Lopez-de-Ipina K, Satue-Villar A, Faundez-Zanuy M, et al. Advances in a multimodal approach for dysphagia analysis based on automatic voice analysis. In: Bassis S, Esposito A, Morabito F, et al., editors. Advances in Neural Networks. WIRN 2015. Smart Innovation, Systems and Technologies, vol 54. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-33747-0_20","DOI":"10.1007\/978-3-319-33747-0_20"},{"key":"10.14639\/0392-100X-N2309_ref5","doi-asserted-by":"crossref","unstructured":"Cohen SM, Dupont WD, Courey MS. Quality-of-life impact of non-neoplastic voice disorders: a meta-analysis. Ann Otol Rhinol Laryngol 2006;115:128-134. https:\/\/doi.org\/10.1177\/000348940611500209","DOI":"10.1177\/000348940611500209"},{"key":"10.14639\/0392-100X-N2309_ref6","doi-asserted-by":"crossref","unstructured":"Mekyska J, Janousova E, Gomez-Vilda P, et al. Robust and complex approach of pathological speech signal analysis. Neurocomputing 2015;167:94-111. https:\/\/doi.org\/10.1016\/j.neucom.2015.02.085","DOI":"10.1016\/j.neucom.2015.02.085"},{"key":"10.14639\/0392-100X-N2309_ref7","doi-asserted-by":"crossref","unstructured":"Dankovicov\u00e1 Z, Sov\u00e1k D, Drot\u00e1r P, et al. Machine learning approach to dysphonia detection. Appl Sci 2018;8:1927. https:\/\/doi.org\/10.3390\/app8101927","DOI":"10.3390\/app8101927"},{"key":"10.14639\/0392-100X-N2309_ref8","doi-asserted-by":"crossref","unstructured":"Zhan A, Mohan S, Tarolli C, et al. Using smartphones and machine learning to quantify Parkinson disease severity: the mobile Parkinson disease score. JAMA Neurol 2018;75:876-880. https:\/\/doi.org\/10.1001\/jamaneurol.2018.0809","DOI":"10.1001\/jamaneurol.2018.0809"},{"key":"10.14639\/0392-100X-N2309_ref9","doi-asserted-by":"crossref","unstructured":"Suppa A, Asci F, Saggio G, et al. Voice analysis in adductor spasmodic dysphonia: objective diagnosis and response to botulinum toxin. Park Relat Dis 2020;73:23-30. https:\/\/doi.org\/10.1016\/j.parkreldis.2020.03.012","DOI":"10.1016\/j.parkreldis.2020.03.012"},{"key":"10.14639\/0392-100X-N2309_ref10","doi-asserted-by":"crossref","unstructured":"Byeon H. Prevalence of perceived dysphonia and its correlation with prevalence of clinically diagnosed laryngeal disorders: the Korea National health and Nutrition Examination Surveys 2010-2112. Ann Otol Rhinol Laryngol 2015;124:770-776. https:\/\/doi.org\/10.1177\/0003489415583684","DOI":"10.1177\/0003489415583684"},{"key":"10.14639\/0392-100X-N2309_ref11","doi-asserted-by":"crossref","unstructured":"Hah JH, Sim S, An SY, et al. Evaluation of the prevalence of and factors associated with laryngeal diseases among the general population. Laryngoscope 2015;125:2536-2542. https:\/\/doi.org\/10.1002\/lary.25424","DOI":"10.1002\/lary.25424"},{"key":"10.14639\/0392-100X-N2309_ref12","unstructured":"Bohlender J. Diagnostic and therapeutic pitfalls in benign vocal fold diseases. GMS Curr Top Otorhinolaryngol Head Neck Surg 2013;12:Doc01. https:\/\/doi.org\/10.3205\/cto000093"},{"key":"10.14639\/0392-100X-N2309_ref13","unstructured":"Channon F, Stone RE. Nodules and polyps. In: Brown WS, Vinson BP, Crary MA, editors. Organic voice disorders: assessment and treatment. San Diego, CA: Singular; 2000."},{"key":"10.14639\/0392-100X-N2309_ref14","doi-asserted-by":"crossref","unstructured":"Heman-Ackah YD, Sataloff RT, Laureyns G, et al. Quantifying the cepstral peak prominence, a measure of dysphonia. J Voice 2014;28:783-788. https:\/\/doi.org\/10.1016\/j.jvoice.2014.05.005","DOI":"10.1016\/j.jvoice.2014.05.005"},{"key":"10.14639\/0392-100X-N2309_ref15","doi-asserted-by":"crossref","unstructured":"Asci F, Costantini G, Di Leo P, et al. Machine learning analysis of voice samples recorded through smartphones: the combined effect of ageing and gender. Sensors 2020;20:5022. https:\/\/doi.org\/10.3390\/s20185022","DOI":"10.3390\/s20185022"},{"key":"10.14639\/0392-100X-N2309_ref16","doi-asserted-by":"crossref","unstructured":"Hegde S, Shetty S, Rai S, et al. A survey on machine learning approaches for automatic detection of voice disorders. J Voice 2019;33:947. https:\/\/doi.org\/10.1016\/j.jvoice.2018.07.014","DOI":"10.1016\/j.jvoice.2018.07.014"},{"key":"10.14639\/0392-100X-N2309_ref17","unstructured":"ISO 532-1:2017(E). \u201cAcoustics \u2013 methods for calculating loudness \u2013 Part 1: Zwicker method\u201d. International Organization for Standardization. ISO, Geneva; 2017."},{"key":"10.14639\/0392-100X-N2309_ref18","unstructured":"ISO 532-2:2017(E). \u201cAcoustics \u2013 methods for calculating loudness \u2013 Part 2: Moore-Glasberg method\u201d. International Organization for Standardization. ISO, Geneva; 2017."},{"key":"10.14639\/0392-100X-N2309_ref19","doi-asserted-by":"crossref","unstructured":"Chawla N, Bowyer K, Hall L, et al. Smote: synthetic minority over-sampling technique. J Artif Intell Res 2002;16:321-357. https:\/\/doi.org\/10.1613\/jair.953","DOI":"10.1613\/jair.953"},{"key":"10.14639\/0392-100X-N2309_ref20","doi-asserted-by":"crossref","unstructured":"Hu HC, Chang SY, Wang CH, et al. Deep learning application for vocal fold disease prediction through voice recognition: preliminary development study. J Med Internet Res 2021;23:E25247. https:\/\/doi.org\/10.2196\/25247","DOI":"10.2196\/25247"},{"key":"10.14639\/0392-100X-N2309_ref21","doi-asserted-by":"crossref","unstructured":"Pham M, Lin J, Zhang Y. Diagnosing voice disorder with machine learning. IEEE International Conference on Big Data (Big Data) 2018:5263-5266. https:\/\/doi.org\/10.1109\/BigData.2018.8622250","DOI":"10.1109\/BigData.2018.8622250"},{"key":"10.14639\/0392-100X-N2309_ref22","doi-asserted-by":"crossref","unstructured":"Naunheim M, Carroll T. Benign vocal fold lesions: update on nomenclature, cause, diagnosis, and treatment. Curr Opin Otolaryngol Head Neck Surg 2017;25:1. https:\/\/doi.org\/10.1097\/MOO.0000000000000408","DOI":"10.1097\/MOO.0000000000000408"},{"key":"10.14639\/0392-100X-N2309_ref23","doi-asserted-by":"crossref","unstructured":"Dikkers FG, Nikkels PJ. Benign lesions of the vocal folds: histopathology and phonotrauma. Ann Otol Rhinol Laryngol 1995;104:698-703. https:\/\/doi.org\/10.1177\/000348949510400905","DOI":"10.1177\/000348949510400905"},{"key":"10.14639\/0392-100X-N2309_ref24","doi-asserted-by":"crossref","unstructured":"P\u00e9piot E, Arnold A. Cross-Gender Differences in English\/French Bilingual Speakers: A Multiparametric Study. Percept Mot Skills 2021;128:153-177. https:\/\/doi.org\/10.1177\/0031512520973514.","DOI":"10.1177\/0031512520973514"},{"key":"10.14639\/0392-100X-N2309_ref25","doi-asserted-by":"crossref","unstructured":"Malik P, Yadav S, Sen RD, et al. The clinicopathological study of benign lesions of vocal cords. Indian J Otolaryngol 2017;71:212-220. https:\/\/doi.org\/10.1007\/s12070-017-1240-0","DOI":"10.1007\/s12070-017-1240-0"},{"key":"10.14639\/0392-100X-N2309_ref26","doi-asserted-by":"crossref","unstructured":"Varma S, Simon R. Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 2006;8. https:\/\/doi.org\/10.1186\/1471-2105-7-91","DOI":"10.1186\/1471-2105-7-91"},{"key":"10.14639\/0392-100X-N2309_ref27","doi-asserted-by":"crossref","unstructured":"Unger J, Schuster M, Hecker D, et al. A multiscale product approach for an automatic classification of voice disorders from endoscopic high-speed videos. Annu Int Conf IEEE Eng Med Biol Soc 2013;2013:7360-7363. https:\/\/doi.org\/10.1109\/EMBC.2013.6611258","DOI":"10.1109\/EMBC.2013.6611258"}],"container-title":["Acta Otorhinolaryngologica Italica"],"original-title":[],"link":[{"URL":"https:\/\/www.actaitalica.it\/article\/view\/2309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T07:21:39Z","timestamp":1729668099000},"score":1,"resource":{"primary":{"URL":"https:\/\/old.actaitalica.it\/article\/view\/2309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":27,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,10]]}},"URL":"https:\/\/doi.org\/10.14639\/0392-100x-n2309","relation":{},"ISSN":["1827-675X"],"issn-type":[{"value":"1827-675X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]},"article-number":"3"}}