Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems

Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems | 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 Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems Ethan J. Turner, Grace L. Mitchell, Liam R. Scott, Chloe A. Wright, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7808032/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 Real-time speech systems must balance fast response with reliable protection against attacks. This study introduces a mixed-signal framework that links C++ modules with DSP units, combining efficient feature extraction and instruction parsing with secure sandboxing. Tests were carried out on mobile and smart home devices under quiet, office, and street-noise settings. The system reduced response latency by about 34% compared with software-only designs and improved recognition accuracy by 2.5–4.6 percentage points. It kept latency below 110 ms in all acoustic conditions and lowered replay and injection attack success rates by 40–60% through adaptive control. An ablation study showed that both sandboxing and adaptive checks are required to keep these gains. The results highlight the novelty of joining low-latency processing with strong protection, offering practical value for safety-related speech systems, while also noting limits in scaling to larger vocabularies and energy use on resource-constrained devices. Theoretical Computer Science Electrical Engineering real-time speech systems mixed-signal framework DSP acceleration latencyreduction sandboxing replay attack smart devices 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-7808032","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":526533739,"identity":"797ba367-c06b-479e-9338-ddd9a65308e6","order_by":0,"name":"Ethan J. Turner","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIiWNgGAWjYBACPhDB2ABmJz5IqABSzMwNeLWwIWl5bPDhDEgLI9FaGJ9JzmxDMgGnFonkZw9/7jgsb86/OE2ad15tNH87UMuPim14tKSZG/OeOWy4c8azZGvebcdzZxxmbGDsOXMbj5YEM2nGtsOMG26cSbzNu+1YbgNQCzNjGz4t6d8kf7Ydtt9w4/wHad45x3LnE9aSYybB23Y4ccP5hiTJmQ01uRsIauF5UybN25aevOEGQ7LBh2MHcjcCtRzE5xd+9vRtQIdZ2244fwAYlTV1ufPOHz744EcFbi0IIJEAIg+D2QeIUA+yD6yujjjFo2AUjIJRMKIAAP0eYVVd16ftAAAAAElFTkSuQmCC","orcid":"","institution":"Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, Canada","correspondingAuthor":true,"prefix":"","firstName":"Ethan","middleName":"J.","lastName":"Turner","suffix":""},{"id":526533740,"identity":"a14c807b-424b-419c-adef-2e986779d88f","order_by":1,"name":"Grace L. Mitchell","email":"","orcid":"","institution":"School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia","correspondingAuthor":false,"prefix":"","firstName":"Grace","middleName":"L.","lastName":"Mitchell","suffix":""},{"id":526533741,"identity":"5e1bb2cb-32dd-4040-8922-e379ebfaadfb","order_by":2,"name":"Liam R. Scott","email":"","orcid":"","institution":"Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, Canada","correspondingAuthor":false,"prefix":"","firstName":"Liam","middleName":"R.","lastName":"Scott","suffix":""},{"id":526533742,"identity":"75c6fbbd-aab3-4d2e-aff9-65a4d5a5bb0c","order_by":3,"name":"Chloe A. Wright","email":"","orcid":"","institution":"School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia","correspondingAuthor":false,"prefix":"","firstName":"Chloe","middleName":"A.","lastName":"Wright","suffix":""},{"id":526533743,"identity":"59a60c38-9a82-422d-b098-d968f4ec09c8","order_by":4,"name":"Isabella M. Parker","email":"","orcid":"","institution":"Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, Canada","correspondingAuthor":false,"prefix":"","firstName":"Isabella","middleName":"M.","lastName":"Parker","suffix":""}],"badges":[],"createdAt":"2025-10-08 12:43:48","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-7808032/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7808032/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93130870,"identity":"ee7bf0f9-8298-41bc-aebc-88b6aec50fc0","added_by":"auto","created_at":"2025-10-09 11:30:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":529678,"visible":true,"origin":"","legend":"","description":"","filename":"9.2703chenMixedSignalDesignUsingCandDSPAccelerationforLowLatencyandSecureSpeechSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7808032/v1_covered_50b2d15a-7b6e-4a3e-88e3-da819e085e35.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eMixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems\u003c/strong\u003e\u003c/p\u003e","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":"real-time speech systems, mixed-signal framework, DSP acceleration, latencyreduction, sandboxing, replay attack, smart devices","lastPublishedDoi":"10.21203/rs.3.rs-7808032/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7808032/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eReal-time speech systems must balance fast response with reliable protection against attacks. This study introduces a mixed-signal framework that links C++ modules with DSP units, combining efficient feature extraction and instruction parsing with secure sandboxing. Tests were carried out on mobile and smart home devices under quiet, office, and street-noise settings. The system reduced response latency by about 34% compared with software-only designs and improved recognition accuracy by 2.5–4.6 percentage points. It kept latency below 110 ms in all acoustic conditions and lowered replay and injection attack success rates by 40–60% through adaptive control. An ablation study showed that both sandboxing and adaptive checks are required to keep these gains. The results highlight the novelty of joining low-latency processing with strong protection, offering practical value for safety-related speech systems, while also noting limits in scaling to larger vocabularies and energy use on resource-constrained devices.\u003c/p\u003e","manuscriptTitle":"Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-09 11:22:07","doi":"10.21203/rs.3.rs-7808032/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":"fc56f65a-dfd6-4010-9ea9-80370539a3f1","owner":[],"postedDate":"October 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55964384,"name":"Theoretical Computer Science"},{"id":55964385,"name":"Electrical Engineering"}],"tags":[],"updatedAt":"2025-10-09T11:22:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-09 11:22:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7808032","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7808032","identity":"rs-7808032","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}