A Multifaceted Dimensionality Reduction Pipeline for Bangla Speech Emotion Recognition

A Multifaceted Dimensionality Reduction Pipeline for Bangla Speech Emotion Recognition | 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 A Multifaceted Dimensionality Reduction Pipeline for Bangla Speech Emotion Recognition Abu Omayed This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9643770/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 Speech Emotion Recognition (SER) in resource-starved languages such as Bangla necessitates resilient acoustic modeling techniques to counteract the challenges of sparse data and noise sensitivity. In this paper, we propose an extensive set of feature extraction approaches involving multiple time-domain, frequency-domain, and time-frequency acoustic features. A collection of distinctive characteristics, namely Amplitude Envelope, Zero Crossing Rate (ZCR), MFCCs, and Spectral Centroid, is derived using higher-order statistics. To tackle the issues of excessive computation and redundant data associated with large-scale acoustic feature sets, we proposed a multifaceted dimensionality reduction pipeline based on Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA). The effectiveness of the designed signal processing pipeline is corroborated using two different benchmark datasets, namely SUBESCO (7 classes) and KBES (9 classes). Experimental evaluations have confirmed that an Extra Tree classifier, when coupled with the feature-reduction technique presented in this paper, can reach a maximum accuracy of 94.44% and 90.86% on KBES and SUBESCO, respectively. Speech Emotion Recognition Feature Fusion Dimensionality Reduction Acoustic Features Audio Signal Processing Bangla NLP 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-9643770","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":638022117,"identity":"821cadc5-b476-469b-9dfc-87fb93402361","order_by":0,"name":"Abu Omayed","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYDACCRjjeAOQMLAgRcuZAyAtErhVYmq5kYDCxQ34Z/cYPrpRc1iO7+bzqxt+FEgw8Ld3J+C35M4ZY+OcY4eNJW/nlN3sATpM4szZDfituZFjJp3Ddjhxw+2ctBs8QC0GErn4tciDtfw7XL/h5pm0m3+I0WIA0pLbdjjB4Ab7sdtE2WJ451ixcW5fuuHMMzlst2UMJHgI+kXudvPGxznfrOX5jh9/dvPNHxs5/vZeAt6HgGYg5jEAsXiIUQ4CdUDM/oBY1aNgFIyCUTDCAAAEZE0VZzh1KQAAAABJRU5ErkJggg==","orcid":"","institution":"University of Chittagong","correspondingAuthor":true,"prefix":"","firstName":"Abu","middleName":"","lastName":"Omayed","suffix":""}],"badges":[],"createdAt":"2026-05-07 14:23:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9643770/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9643770/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109094678,"identity":"30258054-29b3-4512-a891-81370ccab510","added_by":"auto","created_at":"2026-05-12 13:53:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1379241,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9643770/v1_covered_4e12652e-4fc3-4dc6-8785-f3c8df840fdd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multifaceted Dimensionality Reduction Pipeline for Bangla Speech Emotion Recognition","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":"Speech Emotion Recognition, Feature Fusion, Dimensionality Reduction, Acoustic Features, Audio Signal Processing, Bangla NLP","lastPublishedDoi":"10.21203/rs.3.rs-9643770/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9643770/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSpeech Emotion Recognition (SER) in resource-starved languages such as Bangla necessitates resilient acoustic modeling techniques to counteract the challenges of sparse data and noise sensitivity. In this paper, we propose an extensive set of feature extraction approaches involving multiple time-domain, frequency-domain, and time-frequency acoustic features. A collection of distinctive characteristics, namely Amplitude Envelope, Zero Crossing Rate (ZCR), MFCCs, and Spectral Centroid, is derived using higher-order statistics. To tackle the issues of excessive computation and redundant data associated with large-scale acoustic feature sets, we proposed a multifaceted dimensionality reduction pipeline based on Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA). The effectiveness of the designed signal processing pipeline is corroborated using two different benchmark datasets, namely SUBESCO (7 classes) and KBES (9 classes). Experimental evaluations have confirmed that an Extra Tree classifier, when coupled with the feature-reduction technique presented in this paper, can reach a maximum accuracy of 94.44% and 90.86% on KBES and SUBESCO, respectively.\u003c/p\u003e","manuscriptTitle":"A Multifaceted Dimensionality Reduction Pipeline for Bangla Speech Emotion Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-12 13:12:18","doi":"10.21203/rs.3.rs-9643770/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":"59f42433-cd40-4c2d-bc9e-5d3c507812ee","owner":[],"postedDate":"May 12th, 2026","published":true,"recentEditorialEvents":[{"type":"editorAssigned","content":"","date":"2026-05-11T07:37:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-11T07:37:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Speech Technology","date":"2026-05-07T14:08:00+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T13:12:18+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-12 13:12:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9643770","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9643770","identity":"rs-9643770","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}