Acoustic-Driven Generation of Pathological Speech Reports Using Large Language Models

Acoustic-Driven Generation of Pathological Speech Reports Using Large Language Models | 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 Acoustic-Driven Generation of Pathological Speech Reports Using Large Language Models Tomas Arias-Vergara, Lukas Buess, Nastassia Vysotskaya, Soroosh Tayebi Arasteh, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7326708/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 Clinical reports compile patients' histories, treatments, and outcomes, enabling the creation of personalized and effective treatment plans. However, speech disorders are rarely analyzed using such reports, primarily due to the absence of standardized speech protocols. Nevertheless, speech and language therapists (SLTs) can rely on perceptual evaluations, such as the modified Frenchay Dysarthria Assessment (mFDA) scale, to quantify the severity of symptoms across seven categories: breathing, lips, larynx, palate, monotonicity, tongue, and intelligibility. In this paper, we propose using Large Language Models (LLMs) to generate FDA-like text reports from audio recordings. Furthermore, we improve \textit{user control} over the input to the LLM by extracting acoustic biomarkers (correlated with the categories from the mFDA) and using them as prompts to the language model. For this, we used speech recordings from 50 Parkinson's disease (PD) patients and 50 healthy controls (HC), whose audio recordings were assessed by three SLTs according to the mFDA.Structured reports are generated by feeding acoustic biomarkers that are extracted from the speech signals. For this, we only use acoustic biomarkers that are correlated to the seven categories of the mFDA.The results demonstrate that the LLMs can generate reports with a BLEU score of 0.789 for PD and 0.836 for HC, showing the potential of our proposed approach for practical medical applications. Biological sciences/Computational biology and bioinformatics Health sciences/Health care Health sciences/Medical research Health sciences/Neurology Biological sciences/Neuroscience 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-7326708","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":502066769,"identity":"0438a835-d74a-488d-8188-14e73324a0c3","order_by":0,"name":"Tomas Arias-Vergara","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYDADNgYGxgcVINYBAip5kLQwG5whSQtIlwRRWuzZuxM//mCwy+djP/6s4kDNYQa+4w0EbOE5u1mahyHZso0nx+zGgWOHGSTPELCGRyJ3gzTIG2wMOWy3P7AdZjC4kUBQy+afPxjqDdj4nz8rOPAPqOX+A4JatknwMBw2YJNIMGM42AayBb8OBp4zZ7dZ8xgcB2p5YyxxsC+dR/IMAYext/duvvmjotpAvj/94YcD36zl+I4fIGANGBggWUuM+lEwCkbBKBgFBAAAcgZBzIED3isAAAAASUVORK5CYII=","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":true,"prefix":"","firstName":"Tomas","middleName":"","lastName":"Arias-Vergara","suffix":""},{"id":502066770,"identity":"dbf1aa4b-f87f-41d8-9530-123514421740","order_by":1,"name":"Lukas Buess","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Lukas","middleName":"","lastName":"Buess","suffix":""},{"id":502066771,"identity":"c9f7a10b-cdc1-47fa-b77b-2dac334206ae","order_by":2,"name":"Nastassia Vysotskaya","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Nastassia","middleName":"","lastName":"Vysotskaya","suffix":""},{"id":502066772,"identity":"1927f384-6140-41b8-8fdd-8c6f598956e2","order_by":3,"name":"Soroosh Tayebi Arasteh","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Soroosh","middleName":"Tayebi","lastName":"Arasteh","suffix":""},{"id":502066773,"identity":"b58ace96-1ea1-49c1-afed-bbcb3bc1ea6d","order_by":4,"name":"Juan Rafael Orozco-Arroyave","email":"","orcid":"","institution":"University of Antioquia","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"Rafael","lastName":"Orozco-Arroyave","suffix":""},{"id":502066774,"identity":"7ae61678-320a-47a3-97d8-c0b1858a9cd2","order_by":5,"name":"Maria Schuster","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"","lastName":"Schuster","suffix":""},{"id":502066775,"identity":"972d14ee-8927-4cba-adbb-cc5c0c356a26","order_by":6,"name":"Elmar Noeth","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Elmar","middleName":"","lastName":"Noeth","suffix":""},{"id":502066776,"identity":"5866781c-de49-4843-a365-2fcbb12a56bc","order_by":7,"name":"Andreas Maier","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Andreas","middleName":"","lastName":"Maier","suffix":""},{"id":502066777,"identity":"6e9c5b26-b99a-4d6c-a6b6-d010a186d9e5","order_by":8,"name":"Paula Andrea Perez-Toro","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Paula","middleName":"Andrea","lastName":"Perez-Toro","suffix":""}],"badges":[],"createdAt":"2025-08-08 11:23:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7326708/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7326708/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95183074,"identity":"ecbc9e9d-1ffc-45b8-9b02-9f4fb5b28a45","added_by":"auto","created_at":"2025-11-05 08:39:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":850509,"visible":true,"origin":"","legend":"","description":"","filename":"SpeechLLMsSRv0.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7326708/v1_covered_b611facc-ce38-499d-96c5-f939e114d07a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Acoustic-Driven Generation of Pathological Speech Reports Using Large Language Models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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-7326708/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7326708/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Clinical reports compile patients' histories, treatments, and outcomes, enabling the creation of personalized and effective treatment plans. However, speech disorders are rarely analyzed using such reports, primarily due to the absence of standardized speech protocols. Nevertheless, speech and language therapists (SLTs) can rely on perceptual evaluations, such as the modified Frenchay Dysarthria Assessment (mFDA) scale, to quantify the severity of symptoms across seven categories: breathing, lips, larynx, palate, monotonicity, tongue, and intelligibility. In this paper, we propose using Large Language Models (LLMs) to generate FDA-like text reports from audio recordings. Furthermore, we improve \\textit{user control} over the input to the LLM by extracting acoustic biomarkers (correlated with the categories from the mFDA) and using them as prompts to the language model. For this, we used speech recordings from 50 Parkinson's disease (PD) patients and 50 healthy controls (HC), whose audio recordings were assessed by three SLTs according to the mFDA.Structured reports are generated by feeding acoustic biomarkers that are extracted from the speech signals. For this, we only use acoustic biomarkers that are correlated to the seven categories of the mFDA.The results demonstrate that the LLMs can generate reports with a BLEU score of 0.789 for PD and 0.836 for HC, showing the potential of our proposed approach for practical medical applications.","manuscriptTitle":"Acoustic-Driven Generation of Pathological Speech Reports Using Large Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-19 17:34:30","doi":"10.21203/rs.3.rs-7326708/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":"f249fa70-4548-446c-82eb-4bbc126483ee","owner":[],"postedDate":"August 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53326591,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":53326592,"name":"Health sciences/Health care"},{"id":53326593,"name":"Health sciences/Medical research"},{"id":53326594,"name":"Health sciences/Neurology"},{"id":53326595,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2025-11-05T08:39:04+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-19 17:34:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7326708","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7326708","identity":"rs-7326708","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}