Aligning syntactic structure to the dynamics of verbal communication: a pipeline for annotating syntactic phrases onto speech acoustics | 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 Resource Aligning syntactic structure to the dynamics of verbal communication: a pipeline for annotating syntactic phrases onto speech acoustics Cosimo Iaia, Alessandro Tavano This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5625187/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 06 Aug, 2025 Read the published version in Behavior Research Methods → Version 1 posted You are reading this latest preprint version Abstract To investigate how the human brain encodes the complex dynamics of natural languages, any viable and reproducible analysis pipeline must rely on either manual annotations or Natural Language Processing (NLP) tools, which extract relevant physical (e.g., acoustic, gestural), and structure- building information from both speech and language signals. However, correctly annotating syntactic structure for a given human language is arguably a harder task than annotating the onset and offset of speech units such as phonemes and syllables, as the latter can be identified by relying at least in part on the physically overt and temporally measurable properties of the signal, while syntactic structure units are generally covert and their labelling is model-driven. We describe and validate a pipeline that takes into account both physical and theoretical aspects of speech and language signals, and operates a theory-driven and explicit alignment between overt speech units and covert syntactic units. Social science/Language and linguistics Social science/Psychology syntax alignment language neural tracking annotation Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 06 Aug, 2025 Read the published version in Behavior Research Methods → 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-5625187","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Resource","associatedPublications":[],"authors":[{"id":389487062,"identity":"f53ed7b4-1688-4e59-8064-be4d74f94a72","order_by":0,"name":"Cosimo Iaia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYBACNgbmww8S/9gAmYyNB4jUwpZm8LEhDaSlgTgtDAw8BpIzGw6DmcRp4WM/Y2DMu+O83dr2w0BbamyiCTuMJ63gMe+Z28nbziQCtRxLy20gqEWCeYMxD9vtZLMDQC2MDYeJ0cJgIM3Ddi7Z7PxDorWwAL3fdsDO7AbRtvCkpRl8OJOcYHYDaEsCMX6Rbz98+EFChZ292fn0hw8+1NgQ1gIDiWCVCcQqBwF7UhSPglEwCkbBCAMAFi9GEA1jcq4AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-4317-4540","institution":"Goethe University","correspondingAuthor":true,"prefix":"","firstName":"Cosimo","middleName":"","lastName":"Iaia","suffix":""},{"id":389487063,"identity":"727716d2-4976-4fbd-9c17-88ddd1b74281","order_by":1,"name":"Alessandro Tavano","email":"","orcid":"","institution":"Goethe University","correspondingAuthor":false,"prefix":"","firstName":"Alessandro","middleName":"","lastName":"Tavano","suffix":""}],"badges":[],"createdAt":"2024-12-11 14:25:53","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5625187/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5625187/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.3758/s13428-025-02747-7","type":"published","date":"2025-08-07T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92603781,"identity":"9a616cd5-9a6b-476b-8309-b3e69743195f","added_by":"auto","created_at":"2025-10-01 14:58:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1423936,"visible":true,"origin":"","legend":"","description":"","filename":"Alignsyntaxpreprint.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5625187/v1_covered_b5686082-3584-4ee9-a7cd-600a88c860e2.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Aligning syntactic structure to the dynamics of verbal communication: a pipeline for annotating syntactic phrases onto speech acoustics","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"syntax, alignment, language, neural tracking, annotation","lastPublishedDoi":"10.21203/rs.3.rs-5625187/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5625187/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"To investigate how the human brain encodes the complex dynamics of natural languages, any viable and reproducible analysis pipeline must rely on either manual annotations or Natural Language Processing (NLP) tools, which extract relevant physical (e.g., acoustic, gestural), and structure- building information from both speech and language signals. However, correctly annotating syntactic structure for a given human language is arguably a harder task than annotating the onset and offset of speech units such as phonemes and syllables, as the latter can be identified by relying at least in part on the physically overt and temporally measurable properties of the signal, while syntactic structure units are generally covert and their labelling is model-driven. We describe and validate a pipeline that takes into account both physical and theoretical aspects of speech and language signals, and operates a theory-driven and explicit alignment between overt speech units and covert syntactic units.","manuscriptTitle":"Aligning syntactic structure to the dynamics of verbal communication: a pipeline for annotating syntactic phrases onto speech acoustics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-13 04:24:39","doi":"10.21203/rs.3.rs-5625187/v1","editorialEvents":[],"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":"f76b1077-16b1-4a24-8fa7-d89852cb3aab","owner":[],"postedDate":"December 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":41510783,"name":"Social science/Language and linguistics"},{"id":41510784,"name":"Social science/Psychology"}],"tags":[],"updatedAt":"2025-10-01T14:49:46+00:00","versionOfRecord":{"articleIdentity":"rs-5625187","link":"https://doi.org/10.3758/s13428-025-02747-7","journal":{"identity":"behavior-research-methods","isVorOnly":true,"title":"Behavior Research Methods"},"publishedOn":"2025-08-07 00:00:00","publishedOnDateReadable":"August 7th, 2025"},"versionCreatedAt":"2024-12-13 04:24:39","video":"","vorDoi":"10.3758/s13428-025-02747-7","vorDoiUrl":"https://doi.org/10.3758/s13428-025-02747-7","workflowStages":[]},"version":"v1","identity":"rs-5625187","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5625187","identity":"rs-5625187","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.