{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T23:46:08Z","timestamp":1780616768094,"version":"3.54.1"},"reference-count":35,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011790","name":"Xiangya Hospital, Central South University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011790","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007689","name":"Universidade de Aveiro","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007689","id-type":"DOI","asserted-by":"publisher"}]}],"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":[[2026,3]]},"DOI":"10.1016\/j.jvoice.2023.09.024","type":"journal-article","created":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T15:36:04Z","timestamp":1698248164000},"page":"524.e1-524.e11","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":18,"title":["A Voice Disease Detection Method Based on MFCCs and Shallow CNN"],"prefix":"10.1016","volume":"40","author":[{"given":"Xiaoping","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8407-8798","authenticated-orcid":false,"given":"Hao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2023.09.024_bib1","first-page":"94","article-title":"Risk factors and prevalence of voice disorders in different occupational groups\u2014a review of literature","volume":"16","author":"Morawska","year":"2017","journal-title":"Otorynolaryngol Przegla D Kliniczny"},{"key":"10.1016\/j.jvoice.2023.09.024_bib2","doi-asserted-by":"crossref","unstructured":"G\u00f3mez, P, Mart\u00ednez R, D\u00edaz F, et al., \u201cVoice pathology detection by vocal cord biomechanical parameter estimation,\u201d Nonlinear Analyses and Algorithms for Speech Processing: International Conference on Non-Linear Speech Processing. 2005: 242\u2013256.","DOI":"10.1007\/11613107_21"},{"key":"10.1016\/j.jvoice.2023.09.024_bib3","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.jvoice.2016.01.014","article-title":"Investigation of voice pathology detection and classification on different frequency regions using correlation functions","volume":"vol. 31","author":"Al-nasheri","year":"2017","journal-title":"J. Voice"},{"key":"10.1016\/j.jvoice.2023.09.024_bib4","doi-asserted-by":"crossref","first-page":"64514","DOI":"10.1109\/ACCESS.2020.2984925","article-title":"A survey of voice pathology surveillance systems based on Internet of Things and machine learning algorithms","volume":"8","author":"Al-Dhief","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2023.09.024_bib5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2009\/159234","article-title":"Analysis of acoustic features in speakers with cognitive disorders and speech impairments","volume":"2009","author":"Saz","year":"2009","journal-title":"EURASIP J Adv Signal Process"},{"key":"10.1016\/j.jvoice.2023.09.024_bib6","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1097\/MOO.0b013e3282fe96ce","article-title":"Voice assessment: updates on perceptual, acoustic, aerodynamic, and endoscopic imaging methods","volume":"16","author":"Mehta","year":"2008","journal-title":"Curr Opin Otolaryngol Head Neck Surg"},{"key":"10.1016\/j.jvoice.2023.09.024_bib7","doi-asserted-by":"crossref","unstructured":"uanbo WY, Changwei Z, Ziqi F, et al. Voice pathology detection and multi-classification using machine learning classifiers, in Proc. Int. Conf. Sens., Meas. Data Anal. Era Artif. Intell. (ICSMD). 2020: 19\u2013324.","DOI":"10.1109\/ICSMD50554.2020.9261710"},{"key":"10.1016\/j.jvoice.2023.09.024_bib8","doi-asserted-by":"crossref","unstructured":"Murthy, G.L.N., Iswarya V., Sri K.R., et al., \u201cA Novel Algorithm for Detecting Spasmodic Dysphonia Voice Pathology using Random Forest Framework,\u201d 2022 International Conference on Edge Computing and Applications (ICECAA). 2022:800\u2013804.","DOI":"10.1109\/ICECAA55415.2022.9936567"},{"key":"10.1016\/j.jvoice.2023.09.024_bib9","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1288\/00005537-197402000-00012","article-title":"Evaluation and treatment of vocal cord paralysis","volume":"84","author":"Maisel","year":"1974","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2023.09.024_bib10","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1111\/j.1365-2273.1988.tb00280.x","article-title":"Vocal cord nodules: a review","volume":"13","author":"Lancer","year":"1988","journal-title":"Clin Otolaryngol Allied Sci"},{"key":"10.1016\/j.jvoice.2023.09.024_bib11","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1109\/OJEMB.2022.3151233","article-title":"Continuous speech for improved learning pathological voice disorders","volume":"3","author":"Wang","year":"2022","journal-title":"IEEE Open J Eng Med Biol"},{"key":"10.1016\/j.jvoice.2023.09.024_bib12","doi-asserted-by":"crossref","unstructured":"Islam, K.A., D. Perez, and J. Li, \u201cA transfer learning approach for the 2018 FEMH voice data challenge.\u201d in 2018 IEEE International Conference on Big Data (Big Data). IEEE, pp. 5252\u20135257, 2018.","DOI":"10.1109\/BigData.2018.8622447"},{"key":"10.1016\/j.jvoice.2023.09.024_bib13","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.compeleceng.2018.04.008","article-title":"A new database of healthy and pathological voices","volume":"68","author":"Cesari","year":"2018","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.jvoice.2023.09.024_bib14","doi-asserted-by":"crossref","unstructured":"Mesallam, T.A., et al., \u201cDevelopment of the arabic voice pathology database and its evaluation by using speech features and machine learning algorithms,\u201d Journal of healthcare engineering. 2017.","DOI":"10.1155\/2017\/8783751"},{"key":"10.1016\/j.jvoice.2023.09.024_bib15","first-page":"143","article-title":"A German database of patterns of pathological vocal fold vibration","volume":"3","author":"P\u00fctzer","year":"1997","journal-title":"Phonus"},{"key":"10.1016\/j.jvoice.2023.09.024_bib16","first-page":"289","article-title":"The advanced voice function assessment databases (AVFAD): tools for voice clinicians and speech research, advances in speech-language pathology","volume":"14","author":"Jesus","year":"2017","journal-title":"IntechOpen"},{"key":"10.1016\/j.jvoice.2023.09.024_bib17","first-page":"3003","article-title":"Voice disorders identification using hybrid approach: Wavelet analysis and multilayer neural networks","volume":"2","author":"Salhi","year":"2008","journal-title":"Int J Electr Comput Eng"},{"key":"10.1016\/j.jvoice.2023.09.024_bib18","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1016\/j.jvoice.2015.06.010","article-title":"Analysis and classification of voice pathologies using glottal signal parameters","volume":"30","author":"Kohler","year":"2016","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2023.09.024_bib19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.bspc.2014.02.001","article-title":"Pathological voice detection and binary classification using MPEG-7 audio features","volume":"11","author":"Muhammad","year":"2014","journal-title":"Biomed Signal Process Control"},{"key":"10.1016\/j.jvoice.2023.09.024_bib20","doi-asserted-by":"crossref","unstructured":"Degila, K., R. Errattahi, and A.E. Hannani,\u201d The UCD system for the 2018 FEMH voice data challenge,\u201d in 2018 IEEE International Conference on Big Data (Big Data). IEEE. 2018:5242\u20135246.","DOI":"10.1109\/BigData.2018.8622604"},{"key":"10.1016\/j.jvoice.2023.09.024_bib21","doi-asserted-by":"crossref","unstructured":"Arias-Londo\u00f1o, J.D., G\u00f3mez-Garc\u00eda J.A., Moro-Vel\u00e1zquez L., et al., \u201cByovoz automatic voice condition analysis system for the 2018 FEMH challenge,\u201d in 2018 IEEE International Conference on Big Data (Big Data). IEEE. 2018:5228\u20135232.","DOI":"10.1109\/BigData.2018.8622498"},{"key":"10.1016\/j.jvoice.2023.09.024_bib22","doi-asserted-by":"crossref","unstructured":"Chuang, Z.-Y., Yu X.T., Chen J.Y., et al., \u201cDnn-based approach to detect and classify pathological voice,\u201d in 2018 IEEE international conference on big data (big data). IEEE. 2018:5238\u20135241.","DOI":"10.1109\/BigData.2018.8622317"},{"key":"10.1016\/j.jvoice.2023.09.024_bib23","doi-asserted-by":"crossref","unstructured":"Ju, M., Jiang, Z., Chen, Y., et al., \u201cA multi-representation ensemble approach to classifying vocal diseases,\u201d in 2018 IEEE International Conference on Big Data (Big Data). IEEE. 2018:5258\u20135262.","DOI":"10.1109\/BigData.2018.8622093"},{"key":"10.1016\/j.jvoice.2023.09.024_bib24","doi-asserted-by":"crossref","unstructured":"Ramalingam, A., S. Kedari, and C. Vuppalapati, \u201cIEEE FEMH voice data challenge 2018,\u201d in 2018 IEEE International Conference on Big Data (Big Data). IEEE. 2018:5272\u20135276.","DOI":"10.1109\/BigData.2018.8622164"},{"key":"10.1016\/j.jvoice.2023.09.024_bib25","doi-asserted-by":"crossref","unstructured":"Pham, M., J. Lin, and Y. Zhang, \u201cDiagnosing voice disorder with machine learning,\u201d in 2018 IEEE International Conference on Big Data (Big Data). IEEE. 2018:5263\u20135266.","DOI":"10.1109\/BigData.2018.8622250"},{"key":"10.1016\/j.jvoice.2023.09.024_bib26","unstructured":"Maryam P., Karim F., Majumdar S., et al., \u201cPathological voice classification using mel-cepstrum vectors and support vector machine,\u201d arXiv preprint arXiv:1812.07729, 2018."},{"key":"10.1016\/j.jvoice.2023.09.024_bib27","doi-asserted-by":"crossref","unstructured":"Miliaresi, I., K. Poutos, and A. Pikrakis, \u201cCombining acoustic features and medical data in deep learning networks for voice pathology classification,\u201d in 2020 28th European Signal Processing Conference (EUSIPCO). IEEE. 2021:1190\u20131194.","DOI":"10.23919\/Eusipco47968.2020.9287333"},{"key":"10.1016\/j.jvoice.2023.09.024_bib28","series-title":"Advances in Speech and Language Technologies for Iberian Languages","first-page":"99","article-title":"Voice pathology detection on the Saarbr\u00fccken voice database with calibration and fusion of scores using multifocal toolkit","author":"Mart\u00ednez","year":"2012"},{"key":"10.1016\/j.jvoice.2023.09.024_bib29","first-page":"339","article-title":"Artificial neural networks and support vector machine for voice disorders identification","volume":"7","author":"Souissi","year":"2016","journal-title":"Int J Adv Comput Sci Appl"},{"key":"10.1016\/j.jvoice.2023.09.024_bib30","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/s10772-016-9338-4","article-title":"Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson\u2019s disease and healthy people","volume":"19","author":"Benba","year":"2021","journal-title":"Int J Speech Technol"},{"key":"10.1016\/j.jvoice.2023.09.024_bib31","doi-asserted-by":"crossref","unstructured":"Ilapakurti, A., Kedari S., Vuppalapati J.S., et al., \u201cArtificial intelligent (AI) clinical edge for voice disorder detection,\u201d in 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService). IEEE. 2019:340\u2013345.","DOI":"10.1109\/BigDataService.2019.00060"},{"key":"10.1016\/j.jvoice.2023.09.024_bib32","first-page":"19","article-title":"MFCC and its applications in speaker recognition","volume":"1","author":"Tiwari","year":"2010","journal-title":"Int J Emerg Technol"},{"key":"10.1016\/j.jvoice.2023.09.024_bib33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et al., \u201cGoing deeper with convolutions,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition. 2015:1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.jvoice.2023.09.024_bib34","first-page":"3094","article-title":"A universal approximation theorem of deep neural networks for expressing probability distributions","volume":"33","author":"Lu","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.jvoice.2023.09.024_bib35","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J Mach Learn Res"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199723003016?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199723003016?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:00:01Z","timestamp":1772568001000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199723003016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["S0892199723003016"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2023.09.024","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A Voice Disease Detection Method Based on MFCCs and Shallow CNN","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2023.09.024","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Voice Foundation. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}