{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:40:39Z","timestamp":1792777239882,"version":"4.5.0"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:00:00Z","timestamp":1792713600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["25BYY150"],"award-info":[{"award-number":["25BYY150"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Phonation-induced acoustic variability, particularly in whispered speech, poses persistent challenges for stable vowel representation. Conventional static formant-based descriptors often fail to capture the dynamic spectral behavior of vowels under such conditions. This study evaluates the robustness of acoustic feature representations for Japanese vowels across normal and whispered phonation, comparing static formant measures with dynamic spectral features derived from Vowel Inherent Spectral Change (VISC). Dynamic features are used to characterize continuous formant trajectory patterns, while Support Vector Machine (SVM) and Random Forest (RF) classifiers serve as analytical probes to assess representation stability rather than as targets of algorithmic optimization. Results demonstrate that incorporating dynamic spectral information leads to more consistent vowel discrimination across phonation types compared to static-only representations, with similar performance trends observed across classification frameworks. These findings suggest that differences in classification outcomes are primarily driven by properties of the acoustic representations rather than by model choice. The study highlights the im-portance of representation-level design for robust speech signal analysis under phonation-induced variability and supports the use of low-dimensional dynamic features for vowel modeling in variable phonation conditions.<\/jats:p>","DOI":"10.1371\/journal.pone.0361125","type":"journal-article","created":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:22:49Z","timestamp":1792776169000},"page":"e0361125","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust acoustic representation of Japanese vowels under phonation variability using dynamic spectral analysis"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5575-2010","authenticated-orcid":true,"given":"Yanlong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Japanese Culture and Economics, Xi\u2019an International Studies University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxiang","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Japanese Culture and Economics, Xi\u2019an International Studies University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueheng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Japanese Culture and Economics, Xi\u2019an International Studies University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,23]]},"reference":[{"key":"pone.0361125.ref001","first-page":"19","article-title":"Accelerate scientific and technological innovation and breakthroughs in language intelligence","author":"J Zhou","year":"2020","journal-title":"People\u2019s Daily"},{"issue":"4","key":"pone.0361125.ref002","first-page":"2","article-title":"On interdisciplinary development of linguistics under the background of new liberal arts discipline construction","author":"W Dai","year":"2020","journal-title":"Foreign Lang World"},{"key":"pone.0361125.ref003","first-page":"14","article-title":"Advances in intelligent voice interaction technology","volume":"5","author":"B Wang","year":"2020","journal-title":"Artif Intell VIEW"},{"issue":"1","key":"pone.0361125.ref004","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s41060-023-00475-9","article-title":"Speech-based detection of multi-class Alzheimer\u2019s disease classification using machine learning","volume":"18","author":"T Tripathi","year":"2023","journal-title":"Int J Data Sci Anal"},{"issue":"3","key":"pone.0361125.ref005","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1080\/02564602.2017.1293570","article-title":"Acoustic\u2013phonetic analysis for speech recognition: A review","volume":"35","author":"BD Sarma","year":"2017","journal-title":"IETE Tech Rev"},{"key":"pone.0361125.ref006","volume-title":"Acoustic theory of speech production","author":"G Fant","year":"1960"},{"key":"pone.0361125.ref007","volume-title":"Acoustic phonetics","author":"KN Stevens","year":"2000"},{"key":"pone.0361125.ref008","volume-title":"A Course in Phonetics","author":"P Ladefoged","year":"2014","edition":"7"},{"issue":"5","key":"pone.0361125.ref009","first-page":"2041669516671320","article-title":"Speaker-sex discrimination for voiced and whispered vowels at short durations","volume":"7","author":"DRR Smith","year":"2016","journal-title":"Percept"},{"key":"pone.0361125.ref010","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.engappai.2016.12.012","article-title":"Whispered speech recognition using deep denoising autoencoder","volume":"59","author":"\u0110T Grozdi\u0107","year":"2017","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0361125.ref011","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1109\/SLT48900.2021.9383595","article-title":"End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training.","volume-title":"2021 IEEE Spoken Language Technology Workshop (SLT)","author":"H-J Chang","year":"2021"},{"issue":"2","key":"pone.0361125.ref012","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.specom.2003.10.005","article-title":"Analysis and recognition of whispered speech","volume":"45","author":"T Ito","year":"2005","journal-title":"Speech Commun"},{"issue":"3","key":"pone.0361125.ref013","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.jvoice.2006.08.012","article-title":"Acoustic analysis of consonants in whispered speech","volume":"22","author":"ST Jovi\u010di\u0107","year":"2008","journal-title":"J Voice"},{"key":"pone.0361125.ref014","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.apacoust.2016.08.007","article-title":"Study of the formant and duration in Chinese whispered vowel speech","volume":"114","author":"Y Zhao","year":"2016","journal-title":"Appl Acoust"},{"issue":"1","key":"pone.0361125.ref015","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"issue":"3","key":"pone.0361125.ref016","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Mach Learn"},{"issue":"09","key":"pone.0361125.ref017","first-page":"918","article-title":"Speech recognition using SVM","volume":"5","author":"R Thiruvengatanadhan","year":"2018","journal-title":"Int Res J Eng Technol"},{"issue":"5","key":"pone.0361125.ref018","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1177\/14707853241255469","article-title":"Not seeing the wood for the trees: Influences on random forest accuracy","volume":"66","author":"C Hand","year":"2024","journal-title":"Int J Mark Res"},{"key":"pone.0361125.ref019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICECIT54077.2021.9641152","article-title":"Comparison between Support Vector Machine and Random Forest for Audio Classification.","volume-title":"2021 International Conference on Electronics, Communications and Information Technology (ICECIT)","author":"MR Ansari","year":"2021"},{"key":"pone.0361125.ref020","unstructured":"Devi TC, Thaoroijam K. Vowel-based Meeteilon dialect identification using a random forest classifier. ArXiv Preprint. 2021. https:\/\/arxiv.org\/abs\/2107.13419"},{"issue":"10","key":"pone.0361125.ref021","doi-asserted-by":"crossref","first-page":"459","DOI":"10.3390\/a17100459","article-title":"Hybrid RFSVM: Hybridization of SVM and random forest models for detection of fake news","volume":"17","author":"DG Dev","year":"2024","journal-title":"Algorithms"},{"key":"pone.0361125.ref022","doi-asserted-by":"crossref","first-page":"133","DOI":"10.21437\/Eurospeech.1999-37","article-title":"Acoustic nature of the whisper.","volume-title":"Eurospeech","author":"M Matsuda","year":"1999"},{"issue":"6","key":"pone.0361125.ref023","first-page":"1079","article-title":"Formant comparison between whispered and voiced vowels in Mandarin","volume":"91","author":"LX Li","year":"2005","journal-title":"Acta Acust United Acust"},{"issue":"2","key":"pone.0361125.ref024","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvoice.2010.12.002","article-title":"A comprehensive vowel space for whispered speech","volume":"26","author":"HR Sharifzadeh","year":"2012","journal-title":"J Voice"},{"key":"pone.0361125.ref025","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/978-3-642-14209-3_2","article-title":"Static and dynamic approaches to vowel perception.","volume-title":"Vowel Inherent Spectral Change","author":"JM. Hillenbrand","year":"2013"},{"key":"pone.0361125.ref026","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/978-3-642-14209-3_5","article-title":"Dynamic specification of coarticulated vowels.","volume-title":"Vowel inherent spectral change","author":"W Strange","year":"2013"},{"issue":"1","key":"pone.0361125.ref027","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1017\/S136672891200051X","article-title":"Intelligibility of American English vowels of native and non-native speakers in quiet and speech-shaped noise","volume":"16","author":"C Liu","year":"2013","journal-title":"Biling Lang Cogn"},{"issue":"2","key":"pone.0361125.ref028","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1250\/ast.39.160","article-title":"African American women\u2019s speech: Vowel inherent spectral change","volume":"39","author":"Y Feimster Holt","year":"2018","journal-title":"Acoust Sci Technol"},{"issue":"5","key":"pone.0361125.ref029","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1121\/1.394433","article-title":"Modeling the role of inherent spectral change in vowel identification","volume":"80","author":"TM Nearey","year":"1986","journal-title":"J Acoust Soc Am"},{"issue":"2","key":"pone.0361125.ref030","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1121\/1.1337959","article-title":"Effects of consonant environment on vowel formant patterns","volume":"109","author":"JM Hillenbrand","year":"2001","journal-title":"J Acoust Soc Am"},{"key":"pone.0361125.ref031","doi-asserted-by":"crossref","first-page":"110362","DOI":"10.1016\/j.apacoust.2024.110362","article-title":"Acoustic characteristics of whispered vowels: A dynamic feature exploration","volume":"228","author":"T Cao","year":"2025","journal-title":"Appl Acoust"},{"key":"pone.0361125.ref032","article-title":"JVS corpus: free Japanese multi-speaker voice corpus","author":"S Takamichi","year":"2019","journal-title":"arXiv"},{"issue":"12","key":"pone.0361125.ref033","doi-asserted-by":"crossref","first-page":"469","DOI":"10.3390\/bs12120469","article-title":"The acquisition of \/\u026a\/\u2013\/i\u02d0\/ is challenging: Perceptual and production evidence from Cypriot Greek speakers of English","volume":"12","author":"GP Georgiou","year":"2022","journal-title":"Behav Sci"},{"issue":"1","key":"pone.0361125.ref034","doi-asserted-by":"crossref","first-page":"15594","DOI":"10.1038\/s41598-023-42818-3","article-title":"Comparison of the prediction accuracy of machine learning algorithms in crosslinguistic vowel classification","volume":"13","author":"GP Georgiou","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0361125.ref035","doi-asserted-by":"crossref","unstructured":"Dihingia L, Bannulmath P, Chowdhury AR, Prasanna SRM, Deepak KT, Sheikh T. Preliminary analysis of lambani vowels and vowel classification using acoustic features. In: International conference on speech and computer. Springer; 2023. p. 195\u2013207.","DOI":"10.1007\/978-3-031-48312-7_16"},{"key":"pone.0361125.ref036","doi-asserted-by":"crossref","unstructured":"James J, Balamurali BT, Abeysinghe B, Liu J. Explaining spectrograms in machine learning: A study on neural networks for speech classification. In: International conference on artificial intelligence and speech technology. 2023. p. 311\u201322.","DOI":"10.1007\/978-3-031-75164-6_23"},{"key":"pone.0361125.ref037","doi-asserted-by":"crossref","unstructured":"Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory, 1992. p. 144\u201352. https:\/\/doi.org\/10.1145\/130385.130401","DOI":"10.1145\/130385.130401"},{"issue":"2","key":"pone.0361125.ref038","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/72.991427","article-title":"A comparison of methods for multiclass support vector machines","volume":"13","author":"CW Hsu","year":"2002","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"pone.0361125.ref039","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"M Fern\u00e1ndez-Delgado","year":"2014","journal-title":"J Mach Learn Res"},{"key":"pone.0361125.ref040","doi-asserted-by":"crossref","unstructured":"Ganapathy S, Thomas S, Hermansky H. Static and dynamic modulation spectrum for speech recognition. In: Interspeech. 2009. p. 2823\u20136. https:\/\/doi.org\/10.21437\/interspeech.2009-721","DOI":"10.21437\/Interspeech.2009-721"},{"key":"pone.0361125.ref041","first-page":"263","article-title":"Vowel inherent spectral change in forensic voice comparison","volume-title":"Vowel inherent spectral change","author":"GS. Morrison","year":"2012"},{"issue":"1","key":"pone.0361125.ref042","article-title":"The phonology of vowel VISC-osity\u2013acoustic evidence and representational implications","volume":"6","author":"G Schwartz","year":"2021","journal-title":"Glossa J Gen Linguist"},{"key":"pone.0361125.ref043","volume-title":"The sounds of the world\u2019s languages","author":"I Maddieson","year":"1996"},{"issue":"5","key":"pone.0361125.ref044","doi-asserted-by":"crossref","first-page":"3099","DOI":"10.1121\/1.411872","article-title":"Acoustic characteristics of American English vowels","volume":"97","author":"J Hillenbrand","year":"1995","journal-title":"J Acoust Soc Am"},{"key":"pone.0361125.ref045","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1007\/978-0-387-84858-7_18","article-title":"High-Dimensional Problems: p \u226b N.","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"T Hastie","year":"2009"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0361125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:22:59Z","timestamp":1792776179000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0361125"}},"subtitle":[],"editor":[{"given":"Laura","family":"Morett","sequence":"first","affiliation":[{"name":"University of Missouri Columbia","place":["UNITED STATES OF AMERICA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,23]]},"references-count":45,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0361125","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,23]]}}}