Sparse mixture of experts for acoustic vector DOA estimation in hybrid noise environments

Sparse mixture of experts for acoustic vector DOA estimation in hybrid noise environments | 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 Sparse mixture of experts for acoustic vector DOA estimation in hybrid noise environments Wenjie Xu, Shichao Yi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6532153/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 Conventional direction-of-arrival (DOA) estimation methods generally rely on the white Gaussian noise assumption, making them ineffective in hybrid noise scenarios. This paper proposes a deep neural network based on sparse mixture of experts (SMoE) framework for DOA estimation in hybrid noise environments. The model first transforms the complex covariance matrix of the array signal into a real covariance matrix via a simple preprocessing method. Subsequently, a CNN is employed to extract spatial features from the array signal. Finally, a SMoE mechanism is utilized to handle hybrid noise conditions. Experiments demonstrate superior performance over traditional methods and CNNs, achieving 0.94° RMSE at 0dB SNR with six noise types. Additionally, we investigate the impact of the model’s tunable parameters on its performance. This work provides a feasible solution for DOA estimation in hybrid noise environments. DOA estimation Deep learning Mixture of expert Hybrid noise Signal processing Sparse gating Full Text Additional Declarations No competing interests reported. Supplementary Files Data.m Noise.m 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-6532153","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452821720,"identity":"58fbc238-1e7f-4031-90fb-9b81eb299ea0","order_by":0,"name":"Wenjie Xu","email":"","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Wenjie","middleName":"","lastName":"Xu","suffix":""},{"id":452821721,"identity":"197d2d21-e010-4065-92b5-919378e16dfd","order_by":1,"name":"Shichao Yi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYDACCcYGZhDNxt6QABE5QLQWngNALQlEaWFgYIYwQMqJ0SI/u7nxc0GNTWKf5INnkj9/MMjx3Uhg/FyAR4vBnYPN0jOOpSW2SSekSfMkMBhL3khglp6BT4tEYhszD9thiBagwxI33EhgY+bB57AZIC3/gFokD6RJ/khgqCeoheEGUAtvG1CLBEOaBNBhCQaEtBjcSGyW5u1LM27jSUi25kmTMJx55mGzNH6HpT/8zPPNRnZ++5nEmz9sbOT5jicf/IzXYVDg2MAAdBU4mhgYG4jQwMBgz8DAfoAolaNgFIyCUTDyAADv6EllIfAz2gAAAABJRU5ErkJggg==","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Shichao","middleName":"","lastName":"Yi","suffix":""}],"badges":[],"createdAt":"2025-04-26 02:23:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6532153/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6532153/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83612818,"identity":"4be1471d-972b-43a4-8b5c-ac14e3027adb","added_by":"auto","created_at":"2025-05-29 12:47:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3248063,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6532153/v1_covered_73ef330a-31af-4ca8-8fbd-da672b292994.pdf"},{"id":82226464,"identity":"3ffa5b0d-2888-4abc-a389-d4ab5a2cb9e7","added_by":"auto","created_at":"2025-05-08 04:27:38","extension":"m","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":2012,"visible":true,"origin":"","legend":"","description":"","filename":"Data.m","url":"https://assets-eu.researchsquare.com/files/rs-6532153/v1/0ca61bc6604db424bae3a935.m"},{"id":82226055,"identity":"6fc23268-0352-46e9-bfc0-98ae66127ef6","added_by":"auto","created_at":"2025-05-08 04:19:38","extension":"m","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2958,"visible":true,"origin":"","legend":"","description":"","filename":"Noise.m","url":"https://assets-eu.researchsquare.com/files/rs-6532153/v1/f30af23dd7a18c9e5effff0b.m"}],"financialInterests":"No competing interests reported.","formattedTitle":"Sparse mixture of experts for acoustic vector DOA estimation in hybrid noise environments","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":"DOA estimation, Deep learning, Mixture of expert, Hybrid noise, Signal processing, Sparse gating","lastPublishedDoi":"10.21203/rs.3.rs-6532153/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6532153/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eConventional direction-of-arrival (DOA) estimation methods generally rely on the white Gaussian noise assumption, making them ineffective in hybrid noise scenarios. This paper proposes a deep neural network based on sparse mixture of experts (SMoE) framework for DOA estimation in hybrid noise environments. The model first transforms the complex covariance matrix of the array signal into a real covariance matrix via a simple preprocessing method. Subsequently, a CNN is employed to extract spatial features from the array signal. Finally, a SMoE mechanism is utilized to handle hybrid noise conditions. Experiments demonstrate superior performance over traditional methods and CNNs, achieving 0.94° RMSE at 0dB SNR with six noise types. Additionally, we investigate the impact of the model’s tunable parameters on its performance. This work provides a feasible solution for DOA estimation in hybrid noise environments.\u003c/p\u003e","manuscriptTitle":"Sparse mixture of experts for acoustic vector DOA estimation in hybrid noise environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-08 04:19:34","doi":"10.21203/rs.3.rs-6532153/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":"9fcc9b17-3ba4-4427-b9b5-52678cdcac21","owner":[],"postedDate":"May 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-29T12:38:49+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-08 04:19:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6532153","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6532153","identity":"rs-6532153","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}