Lip Reading with Deep Learning: A Comprehensive Analysis of Model Architectures

Lip Reading with Deep Learning: A Comprehensive Analysis of Model Architectures | 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 Research Article Lip Reading with Deep Learning: A Comprehensive Analysis of Model Architectures Ahmed cherif This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6502053/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 Lip reading, a pivotal skill in augmenting communication for the hearing impaired, has seen significant advancements with deep learning techniques. This study presents a comprehensive analysis of various deep learning model ar-chitectures for lip reading using a newly constructed dataset, DATAV1. Our investigation explores and evaluates multiple architectures, including ResBlock3D, Conv3D, Conv2D, TimeDis-tributed, attention mechanism and LSTM. Through extensive experimentation and rigorous evaluation metrics, we identify and discuss one of the optimal architectures for accurate lip reading performance, achieving a peak validation accuracy of 98.18%. This research contributes insights into effective model selection and lays groundwork for further advancements in enhancing human-machine communication through lip reading systems. Artificial Intelligence and Machine Learning Lip reading Deep learning Conv3D TimeDis-tributed layers Attention mechanisms LSTM networks Res-Block3D BatchNormalization Full Text Additional Declarations The authors declare no competing interests. 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-6502053","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":446189750,"identity":"748f3ccd-434c-4774-bc70-bc9f207e3df4","order_by":0,"name":"Ahmed cherif","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIie2PMWrDMBRAFf7q4FXFQTpBQcLQdsoxOssU6iWCjBlC661DLmBwoFeoMSSrgiBbd0MzuEunDNrboVLoVmTcrRA90CL+4/2PUCDwH8H2RUghBKNOGYaJ+1TdMAX4rpzfpCdFDFIQpDoyi6xwv31KXK2y7rg8kOsnQLuS4fz5Vr/bypRcFp7I4bXh6/1HOtGA3C2yfrtnVrlLr5Qn08pNMi50VkKsXEXWlXCKyjYehbZy+2mVxxIA6cguxqvc9CrMVsAqAv8ogiaz/gpvZXOx3mvuKm4x/pLM5kow/y2klbU5LjXFsQZjvh4orfLGmMWUeM//veppkg0dd9DiL9OBQCBwDnwDJdZoQSBnM0YAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"cherif","suffix":""}],"badges":[],"createdAt":"2025-04-22 08:28:41","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6502053/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6502053/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81164041,"identity":"13432135-5e6c-4064-93f5-6f16c6ec7754","added_by":"auto","created_at":"2025-04-23 03:32:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":613023,"visible":true,"origin":"","legend":"","description":"","filename":"SecondPaper4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6502053/v1_covered_801e8b91-62ee-44cf-803a-4e1d141a4499.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eLip Reading with Deep Learning: A Comprehensive Analysis of Model Architectures\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Manouba University","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":"Lip reading, Deep learning, Conv3D, TimeDis-tributed layers, Attention mechanisms, LSTM networks, Res-Block3D, BatchNormalization","lastPublishedDoi":"10.21203/rs.3.rs-6502053/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6502053/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLip reading, a pivotal skill in augmenting communication for the hearing impaired, has seen significant advancements with deep learning techniques. This study presents a comprehensive analysis of various deep learning model ar-chitectures for lip reading using a newly constructed dataset, DATAV1. Our investigation explores and evaluates multiple architectures, including ResBlock3D, Conv3D, Conv2D, TimeDis-tributed, attention mechanism and LSTM. Through extensive experimentation and rigorous evaluation metrics, we identify and discuss one of the optimal architectures for accurate lip reading performance, achieving a peak validation accuracy of 98.18%. This research contributes insights into effective model selection and lays groundwork for further advancements in enhancing human-machine communication through lip reading systems.\u003c/p\u003e","manuscriptTitle":"Lip Reading with Deep Learning: A Comprehensive Analysis of Model Architectures","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-23 03:24:01","doi":"10.21203/rs.3.rs-6502053/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":"59db90cc-9287-4841-81ee-34a6a130df35","owner":[],"postedDate":"April 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47491558,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-04-23T03:24:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-23 03:24:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6502053","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6502053","identity":"rs-6502053","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}