Exploring Speech Pattern Disorders in Autism using Machine Learning

Exploring Speech Pattern Disorders in Autism using Machine Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Exploring Speech Pattern Disorders in Autism using Machine Learning Chuanbo Hu, Jacob Thrasher, Wenqi Li, Mindi Ruan, Xiangxu Yu, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6002459/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Diagnosing Autism Spectrum Disorder (ASD) based on speech patterns in examiner-patient dialogues presents significant challenges due to the subtle and varied nature of speech-related symptoms. This study analyzes recorded dialogues using the Autism Diagnostic Observation Schedule (ADOS-2) to identify distinctive speech characteristics. We extracted 40 speech-related features, categorized into intonation, volume, rate, pauses, spectral characteristics, chroma, and duration. These features, analyzed using advanced speech tools, captured complex speech patterns associated with ASD. Machine learning techniques were then applied to classify individuals with ASD, achieving an f1-score of 84.49%. We removed MFCC and Chroma features to focus on prosodic, rhythmic, energy, and selected spectral features associated with the ADOS-2 Module 4 A2 score (i.e., speech abnormalities) to reduce redundancy and balance feature importance. This reduced feature set improved performance, with an accuracy of 85.77% and an F1-score of 86.27%, highlighting the effectiveness of a diverse combination of non-spectral features in ASD diagnosis. While spectral features (e.g., Spectral Centroid, Flux, Rolloff) emerged as key features in the reduced feature set, MFCC 6 and Chroma 4 significantly contributed to classification performance in the full feature set, indicating their role in capturing fine-grained speech variations. Together, these findings support the development of advanced, context-aware models to enhance ASD diagnosis. Biological sciences/Neuroscience/Computational neuroscience/Learning algorithms Health sciences/Biomarkers/Diagnostic markers Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6002459","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":439863572,"identity":"79791f73-0f35-4ec6-a04e-fcd8a376dbbd","order_by":0,"name":"Chuanbo Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYDACCR4G5h8VNXIg9oEHRGthOHPMGKwlgWgtjG3MiQ0gDlFa+Gf3HpMuYGNLnx92+CHQFjs53QZCltw5lyY9g0cmd+PtNAOglmRjswMEtBhI5JhJ8Eiw5W6cnQDSciBxG3FaDJjTDWenfyBeizRPAnOCvHQOkbZI3DljbDnjwDHDDdI5BQcSDIjwC//sHsMbH//VyMvPTt/84UOFnRxBLQgXglUaEKscBOQbSFE9CkbBKBgFIwoAAOMEQt7UeQTaAAAAAElFTkSuQmCC","orcid":"","institution":"University at Albany, State University of New York","correspondingAuthor":true,"prefix":"","firstName":"Chuanbo","middleName":"","lastName":"Hu","suffix":""},{"id":439863573,"identity":"cbc184e7-98c5-4ede-a7cd-331da5c12025","order_by":1,"name":"Jacob Thrasher","email":"","orcid":"","institution":"West Virginia University","correspondingAuthor":false,"prefix":"","firstName":"Jacob","middleName":"","lastName":"Thrasher","suffix":""},{"id":439863575,"identity":"c0cc6fa3-bccd-41b7-9cd4-bc1e6b68a870","order_by":2,"name":"Wenqi Li","email":"","orcid":"","institution":"University at Albany, State University of New York","correspondingAuthor":false,"prefix":"","firstName":"Wenqi","middleName":"","lastName":"Li","suffix":""},{"id":439863578,"identity":"d5a885b9-0ca6-40cf-8986-dc5e83292ed0","order_by":3,"name":"Mindi Ruan","email":"","orcid":"","institution":"University at Albany, State University of New York","correspondingAuthor":false,"prefix":"","firstName":"Mindi","middleName":"","lastName":"Ruan","suffix":""},{"id":439863579,"identity":"93a5c141-7672-4804-8137-f98dbef11807","order_by":4,"name":"Xiangxu Yu","email":"","orcid":"","institution":"Washington University in St. Louis","correspondingAuthor":false,"prefix":"","firstName":"Xiangxu","middleName":"","lastName":"Yu","suffix":""},{"id":439863581,"identity":"fb5531c2-a441-437c-90f8-f1e9a2df2d38","order_by":5,"name":"Lynn K Paul","email":"","orcid":"","institution":"California Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Lynn","middleName":"K","lastName":"Paul","suffix":""},{"id":439863583,"identity":"47259ded-eac0-4a22-af57-caf7f065ee72","order_by":6,"name":"Shuo Wang","email":"","orcid":"","institution":"Washington University in St. Louis","correspondingAuthor":false,"prefix":"","firstName":"Shuo","middleName":"","lastName":"Wang","suffix":""},{"id":439863587,"identity":"57405c7b-e4f0-45de-b828-53627a51af61","order_by":7,"name":"Xin Li","email":"","orcid":"","institution":"University at Albany, State University of New York","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-02-10 23:53:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6002459/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6002459/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81970887,"identity":"c1cf0dbb-abde-4859-9332-aa2c26c1a000","added_by":"auto","created_at":"2025-05-05 12:31:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1781411,"visible":true,"origin":"","legend":"","description":"","filename":"SpeechbasedASDDiagnosisScientificReportsnew.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6002459/v1_covered_54208853-3add-4f32-b05a-e53ce6c498be.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Exploring Speech Pattern Disorders in Autism using Machine Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6002459/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6002459/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Diagnosing Autism Spectrum Disorder (ASD) based on speech patterns in examiner-patient dialogues presents significant challenges due to the subtle and varied nature of speech-related symptoms. This study analyzes recorded dialogues using the Autism Diagnostic Observation Schedule (ADOS-2) to identify distinctive speech characteristics. We extracted 40 speech-related features, categorized into intonation, volume, rate, pauses, spectral characteristics, chroma, and duration. These features, analyzed using advanced speech tools, captured complex speech patterns associated with ASD. Machine learning techniques were then applied to classify individuals with ASD, achieving an f1-score of 84.49%. We removed MFCC and Chroma features to focus on prosodic, rhythmic, energy, and selected spectral features associated with the ADOS-2 Module 4 A2 score (i.e., speech abnormalities) to reduce redundancy and balance feature importance. This reduced feature set improved performance, with an accuracy of 85.77% and an F1-score of 86.27%, highlighting the effectiveness of a diverse combination of non-spectral features in ASD diagnosis. While spectral features (e.g., Spectral Centroid, Flux, Rolloff) emerged as key features in the reduced feature set, MFCC 6 and Chroma 4 significantly contributed to classification performance in the full feature set, indicating their role in capturing fine-grained speech variations. Together, these findings support the development of advanced, context-aware models to enhance ASD diagnosis.","manuscriptTitle":"Exploring Speech Pattern Disorders in Autism using Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-10 02:16:55","doi":"10.21203/rs.3.rs-6002459/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"38054168-961b-44f0-b6c8-84e60dd7be68","owner":[],"postedDate":"April 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46826100,"name":"Biological sciences/Neuroscience/Computational neuroscience/Learning algorithms"},{"id":46826101,"name":"Health sciences/Biomarkers/Diagnostic markers"}],"tags":[],"updatedAt":"2025-05-05T12:23:39+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-10 02:16:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6002459","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6002459","identity":"rs-6002459","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}