Automated Audio Dataset Generation Tool for Classification Tasks in Marine Science | 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 Automated Audio Dataset Generation Tool for Classification Tasks in Marine Science Piotr Gnyś, Gabriela Szczęsna, Antonio C. Domínguez-Brito, Jorge Cabrera-Gámez This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4294773/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 This study presents a comprehensive data processing pipeline designed to convert diverse labeled audio recordings into a uniform labeled dataset suitable for input into machine learning algorithms. The primary emphasis lies in applying this pipeline to marine audio classification, with an illustrative example from this domain serving as experimental validation for the proposed approach. Machine learning dataset generation audio analysis marine science 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-4294773","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":293503921,"identity":"00e0153a-b899-492c-aa02-75834b79ec20","order_by":0,"name":"Piotr Gnyś","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIiWNgGAWjYNCCCgZmECUBxDJEajmD0MJDnA7GNghNnBZz/rXHJH/Ou8PO38B88DYPwx3CWixnvEuT5t32jFniAFuyNQ/DM8JaDG6cMZNm3HaYmeEAj5k0D8Nh4rRI/pxzmFn+AP83IrWc7zGT4G04zGxwgIeNOC2WM3iMrXmOPWM2PMxmbDnHgAi/mPOfMbz5o+ZOstzx5oc33lTckSPsMIkEFmB0HEiGRKbBAYI6GAz4DzB/AGqxg/KJ0DIKRsEoGAUjDgAAHi45Oi/5BK8AAAAASUVORK5CYII=","orcid":"","institution":"Polish Japanese Academy of Information Technology","correspondingAuthor":true,"prefix":"","firstName":"Piotr","middleName":"","lastName":"Gnyś","suffix":""},{"id":293503923,"identity":"5d252f49-b5ce-43ab-88fc-26db31bbeb16","order_by":1,"name":"Gabriela Szczęsna","email":"","orcid":"","institution":"Polish Japanese Academy of Information Technology","correspondingAuthor":false,"prefix":"","firstName":"Gabriela","middleName":"","lastName":"Szczęsna","suffix":""},{"id":293503925,"identity":"557c805c-5a73-4075-b058-6a8eb4b7e13c","order_by":2,"name":"Antonio C. Domínguez-Brito","email":"","orcid":"","institution":"Universidad de las Palmas de Gran Canaria","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"C.","lastName":"Domínguez-Brito","suffix":""},{"id":293503926,"identity":"3436cd6e-2adf-4028-90be-b3b5f9e9cfe4","order_by":3,"name":"Jorge Cabrera-Gámez","email":"","orcid":"","institution":"Universidad de las Palmas de Gran Canaria","correspondingAuthor":false,"prefix":"","firstName":"Jorge","middleName":"","lastName":"Cabrera-Gámez","suffix":""}],"badges":[],"createdAt":"2024-04-19 19:02:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4294773/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4294773/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56187000,"identity":"c823272d-7086-47db-b562-a11a7e05bbcf","added_by":"auto","created_at":"2024-05-09 15:41:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":533495,"visible":true,"origin":"","legend":"","description":"","filename":"pgnyspaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4294773/v1_covered_e208f4c4-0048-404e-b49a-7a38f8d1bd19.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Automated Audio Dataset Generation Tool for Classification Tasks in Marine Science","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Machine learning, dataset generation, audio analysis, marine science","lastPublishedDoi":"10.21203/rs.3.rs-4294773/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4294773/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":" This study presents a comprehensive data processing pipeline designed to convert diverse labeled audio recordings into a uniform labeled dataset suitable for input into machine learning algorithms. The primary emphasis lies in applying this pipeline to marine audio classification, with an illustrative example from this domain serving as experimental validation for the proposed approach.","manuscriptTitle":"Automated Audio Dataset Generation Tool for Classification Tasks in Marine Science","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-24 07:26:41","doi":"10.21203/rs.3.rs-4294773/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":"cacb34c7-2137-463f-a5da-dfbca7a8d0ae","owner":[],"postedDate":"April 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-05-09T15:33:33+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-24 07:26:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4294773","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4294773","identity":"rs-4294773","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.