{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:07:56Z","timestamp":1782173276575,"version":"3.54.5"},"reference-count":44,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2021\/12407-4"],"award-info":[{"award-number":["2021\/12407-4"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["303854\/2022-7"],"award-info":[{"award-number":["303854\/2022-7"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009087","name":"Universidad Industrial de Santander","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009087","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["303854\/2022-7"],"award-info":[{"award-number":["303854\/2022-7"]}],"id":[{"id":"10.13039\/501100003593","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":[[2025,11]]},"DOI":"10.1016\/j.jvoice.2023.05.012","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T07:37:16Z","timestamp":1687160236000},"page":"1431-1439","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"title":["MFCC Parameters of the Speech Signal: An Alternative to Formant-Based Instantaneous Vocal Tract Length\u00a0Estimation"],"prefix":"10.1016","volume":"39","author":[{"given":"P.","family":"Vasquez-Serrano","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.","family":"Reyes-Moreno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodrigo Capobianco","family":"Guido","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Sep\u00falveda-Sep\u00falveda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2023.05.012_bib1","first-page":"1511","article-title":"Morphology and development of the human vocal tract: a study using magnetic resonance imaging","volume":"106","author":"Fitch","year":"1999","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib2","doi-asserted-by":"crossref","unstructured":"Hatano\u00a0H, Kitamura\u00a0T, Takemoto\u00a0H, et al.\u00a0Correlation between vocal tract length, body height, formant frequencies, and pitch frequency for the five Japanese vowels uttered by fifteen male speakers. In: 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, vol. 1, 09\u00a02012.","DOI":"10.21437\/Interspeech.2012-143"},{"key":"10.1016\/j.jvoice.2023.05.012_bib3","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.specom.2012.06.004","article-title":"Automatic estimation of the first three subglottal resonances from adults\u2019 speech signals with application to speaker height estimation","volume":"55","author":"Arsikere","year":"2013","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib4","first-page":"1052","article-title":"Speaker height estimation from speech: fusing spectral regression and statistical acoustic models","volume":"138","author":"Hansen","year":"2015","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib5","unstructured":"Sepulveda-Sepulveda\u00a0A, Castellanos-Dominguez\u00a0G, G\u00f3mez-Vilda\u00a0P.\u00a0Subject-independent acoustic-to-articulatory mapping of fricative sounds by using vocal tract length normalization. Rev Fac Ing Univ Antioq. 2015;12:162\u2013169."},{"key":"10.1016\/j.jvoice.2023.05.012_bib6","first-page":"3248","article-title":"On instantaneous vocal tract length estimation from formant frequencies","volume":"133","author":"Lammert","year":"2013","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0132193","article-title":"On short-time estimation of vocal tract length from formant frequencies","volume":"10","author":"Lammert","year":"2015","journal-title":"PLoS One"},{"key":"10.1016\/j.jvoice.2023.05.012_bib8","first-page":"1292","article-title":"Vocal-tract length estimation","volume":"58","author":"Sorokin","year":"2013","journal-title":"J\u00a0Commun\u00a0Technol\u00a0Electron"},{"key":"10.1016\/j.jvoice.2023.05.012_bib9","first-page":"1213","article-title":"Vocal tract length and formant frequency dispersion correlate with body size in rhesus macaques","volume":"102","author":"Fitch","year":"1997","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib10","first-page":"1904","article-title":"Towards higher precision in vocal tract length estimation","volume":"144","author":"Flego","year":"2018","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib11","first-page":"944","article-title":"Pitch (f0) and formant profiles of human vowels and vowel-like baboon grunts: the role of vocalizer body size and voice-acoustic allometry","volume":"117","author":"Rendall","year":"2005","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib12","first-page":"2859","article-title":"Vocal tract length and acoustics of vocalization in the domestic dog (Canis familiaris)","volume":"202","author":"Riede","year":"1999","journal-title":"J\u00a0Exp\u00a0Biol"},{"key":"10.1016\/j.jvoice.2023.05.012_bib13","first-page":"519","article-title":"Anatomical constraints generate honesty: acoustic cues to age and weight in the roars of red deer stags","volume":"65","author":"Reby","year":"2003","journal-title":"Anim\u00a0Behav"},{"key":"10.1016\/j.jvoice.2023.05.012_bib14","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1111\/j.1439-0310.2006.01247.x","article-title":"Black and white colobus monkey (Colobus guereza) roars as a source of both honest and exaggerated information about body mass","volume":"112","author":"Harris","year":"2006","journal-title":"Ethology"},{"key":"10.1016\/j.jvoice.2023.05.012_bib15","doi-asserted-by":"crossref","unstructured":"Ananthapadmanabha\u00a0T, Ramakrishnan\u00a0A.\u00a0Estimation of the vocal tract length of vowel sounds based on the frequency of the significant spectral valley.\u00a02018;9:2102\u20132106.","DOI":"10.21437\/Interspeech.2018-1105"},{"key":"10.1016\/j.jvoice.2023.05.012_bib16","first-page":"175","article-title":"Control methods used in a study of the vowels","volume":"24","author":"Peterson","year":"2005","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib17","doi-asserted-by":"crossref","unstructured":"Qin\u00a0C, Carreira-Perpi\u00f1\u00e1n\u00a0M. An empirical investigation of the nonuniqueness in the acoustic-to-articulatory mapping.\u00a0Interspeech. 2007:74\u201377.","DOI":"10.21437\/Interspeech.2007-16"},{"key":"10.1016\/j.jvoice.2023.05.012_bib18","first-page":"1535","article-title":"Inversion of articulatory-to-acoustic transformation in the vocal tract by a computer-sorting technique","volume":"63","author":"Atal","year":"1978","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib19","series-title":"Regularization Methods For Ill-Posed Problems","author":"Morozov","year":"1993"},{"key":"10.1016\/j.jvoice.2023.05.012_bib20","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0167-6393(99)00031-X","article-title":"Estimation of stability and accuracy of inverse problem solution for the vocal tract","volume":"30","author":"Sorokin","year":"2000","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib21","series-title":"Proceedings\u00a0of\u00a0Meetings on\u00a0Acoustics Acoustical\u00a0Society\u00a0of\u00a0America","first-page":"11","article-title":"Estimating vocal tract length by minimizing non-uniformity of\u00a0cross-sectional area","volume":"vol. 3","author":"Flego","year":"2018"},{"key":"10.1016\/j.jvoice.2023.05.012_bib22","first-page":"1307","article-title":"Real-time magnetic resonance imaging and electromagnetic articulography database for speech production research (TC)","volume":"136","author":"Narayanan","year":"2014","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib23","unstructured":"Harrison\u00a0PT.\u00a0Making accurate formant measurements: an empirical investigation of the influence of the measurement tool, analysis settings and speaker on formant measurements. 2013."},{"key":"10.1016\/j.jvoice.2023.05.012_bib24","series-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"Huang","year":"2001"},{"key":"10.1016\/j.jvoice.2023.05.012_bib25","first-page":"3989","article-title":"Analysis and prediction of acoustic speech features from mel-frequency cepstral coefficients in distributed speech recognition architectures","volume":"124","author":"Darch","year":"2008","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib26","series-title":"Speech Processing: A Dynamic and Optimization-Oriented Approach","author":"Deng","year":"2003"},{"key":"10.1016\/j.jvoice.2023.05.012_bib27","unstructured":"CSS Templates Market.\u00a0span\u2014USC-TIMIT database. Accedido en 26-04-2018 a.\u00a02014.\u00a0Available at:\u00a0https:\/\/sail.usc.edu\/span\/usc-timit\/index.html."},{"key":"10.1016\/j.jvoice.2023.05.012_bib28","unstructured":"Kim\u00a0J, Kumar\u00a0N, Lee\u00a0S, et al.\u00a0Enhanced airway-tissue boundary segmentation for real-time magnetic resonance imaging data. Proceedings of the 10th International Seminar on Speech Production (ISSP). 2014:222\u2013225."},{"key":"10.1016\/j.jvoice.2023.05.012_bib29","unstructured":"Shue\u00a0Y,\u00a0Keating\u00a0PA,\u00a0Vicenik\u00a0C, et al.\u00a0Voicesauce: a program for voice analysis. In: 17th International Congress of Phonetic Sciences, ICPhS 2011, Hong Kong, China, August 17\u201321, 2011; 2011:1846\u20131849."},{"key":"10.1016\/j.jvoice.2023.05.012_bib30","first-page":"36","article-title":"Formant estimation for speech recognition","volume":"6","author":"Welling","year":"1998","journal-title":"IEEE Trans\u00a0Speech\u00a0Audio Process"},{"key":"10.1016\/j.jvoice.2023.05.012_bib31","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans\u00a0Acoust Speech\u00a0Signal Process"},{"key":"10.1016\/j.jvoice.2023.05.012_bib32","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","article-title":"Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition","volume":"54","author":"Sahidullah","year":"2012","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib33","first-page":"1989","article-title":"Estimation of speaker's height and vocal tract length from speech signal","author":"Dusan","year":"2005","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2023.05.012_bib34","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1109\/TASSP.1978.1163151","article-title":"A posteriori estimation of vocal tract length","volume":"26","author":"Lynn Kirlin","year":"1978","journal-title":"IEEE Trans\u00a0Acoust Speech\u00a0Signal Process"},{"key":"10.1016\/j.jvoice.2023.05.012_bib35","first-page":"268","article-title":"Calculation of vocal tract length","volume":"18","author":"Paige","year":"1970","journal-title":"IEEE Trans\u00a0Audio\u00a0Electroacoust"},{"issue":"7","key":"10.1016\/j.jvoice.2023.05.012_bib36","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0132193","article-title":"On short-time estimation of vocal tract length from formant frequencies","volume":"10","author":"Lammert","year":"2015","journal-title":"PLoS One"},{"key":"10.1016\/j.jvoice.2023.05.012_bib37","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.specom.2007.09.001","article-title":"Statistical mapping between articulatory movements and acoustic spectrum using gaussian mixture models","volume":"50","author":"Toda","year":"2008","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib38","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.specom.2012.06.005","article-title":"Estimation of relevant time-frequency features using Kendall coefficient for articulator position inference","volume":"55","author":"Sep\u00falveda","year":"2013","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib39","series-title":"Neural Networks And Learning Machines","author":"Haykin","year":"2016"},{"key":"10.1016\/j.jvoice.2023.05.012_bib40","first-page":"2162","article-title":"A generalized smoothness criterion for acoustic-to-articulatory inversion","volume":"128","author":"Ghosh","year":"2010","journal-title":"J\u00a0Acoust\u00a0Soc\u00a0Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib41","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.specom.2008.06.005","article-title":"A semi-automatic method for extracting vocal tract movements from x-ray films","volume":"51","author":"Jallon","year":"2009","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib42","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.specom.2007.09.001","article-title":"Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model","volume":"50","author":"Toda","year":"2008","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.05.012_bib43","doi-asserted-by":"crossref","first-page":"3255","DOI":"10.1121\/1.5131271","article-title":"Corner vowels in males and females ages 4 to 20 years: fundamental and f1-f4 formant frequencies","volume":"146","author":"HK","year":"2019","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2023.05.012_bib44","doi-asserted-by":"crossref","unstructured":"Zhao\u00a0X, Wang\u00a0D. Analyzing noise robustness of mfcc and gfcc features in speaker identification.\u00a0In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013:7204\u20137208.","DOI":"10.1109\/ICASSP.2013.6639061"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199723001637?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199723001637?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:36:55Z","timestamp":1778762215000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199723001637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["S0892199723001637"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2023.05.012","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MFCC Parameters of the Speech Signal: An Alternative to Formant-Based Instantaneous Vocal Tract Length\u00a0Estimation","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2023.05.012","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 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"}]}}