Acoustic Feature Synergy and Self-Supervised Learning for Robust Tabla Stroke Classification

Acoustic Feature Synergy and Self-Supervised Learning for Robust Tabla Stroke Classification | 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 Acoustic Feature Synergy and Self-Supervised Learning for Robust Tabla Stroke Classification Jaipreet Kaur, Rajdeep Singh Sohal, Manbir Kaur, Satinder Kaur This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9043295/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 Accurate and robust automatic classification of tabla strokes is essential for music information retrieval and performance analysis, yet remains challenging due to complex timbral structures and subtle acoustic variability across stroke categories. To address this challenge, we propose a robust tabla stroke classification framework that integrates multidomain handcrafted features, spanning spectral, temporal, cepstral, and perceptual descriptors together with self-supervised learning (SSL) representation derived from a newly developed, manually annotated tabla dataset. This dataset is accompanied by an augmented counterpart that simulates realistic acoustic variability, enabling systematic evaluation under domain shift conditions. ANOVA F-test based feature selection is applied to retain the most discriminative attributes, and a range of machine learning classifiers are employed. Experimental results show that multidomain feature synergy significantly improves classification performance, with the Hybrid-8 configuration achieving up to 97.56% accuracy under in-domain evaluation, while SSL representation exhibits superior cross-domain robustness, attaining 94.07% accuracy when trained on original data and tested on augmented data. While handcrafted multidomain features yield near-ceiling accuracy in controlled settings, SSL representation provides stronger resilience to acoustic variability. These findings reveal a trade-off between peak discriminative performance and cross-domain generalization, highlighting the complementary strengths of handcrafted features and SSL representation for developing robust and generalizable tabla stroke classification system. tabla stroke classification multidomain feature extraction handcrafted features self-supervised learning ANOVA feature selection 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-9043295","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":602944700,"identity":"2ce275eb-2223-4764-89c4-97af81bf233d","order_by":0,"name":"Jaipreet Kaur","email":"","orcid":"","institution":"Guru Nanak Dev University","correspondingAuthor":false,"prefix":"","firstName":"Jaipreet","middleName":"","lastName":"Kaur","suffix":""},{"id":602944701,"identity":"1b678d67-cd4b-4811-a703-39a903e2ad15","order_by":1,"name":"Rajdeep Singh Sohal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYHCCBAkog/EBAwMzVIxILcwGxGphgGlhk4BrwQfM2w88vPGh4g4DP/vhY5Vfd1gnNrAffsDwcAduLTJnEpItZ5x5xiDZk5Z2W/ZMemIDT5oBQ+IZfI5KSJPmbTvMYHCDx+y2ZNvhxAaGHAaGxDY8WvgfpEn//XeYwf4G/7disBb+NwS0SABtYWwA2iLBw8b4EaRFgpAtEg+SLXuOPeOROJNmLM3Ylm7cJvHM4AB+h+Uk3vhRc0eOv/3ww48/26xl+/mTHz78iUcLAwNPApA4wANiMoNINhAXnwYGBvYDcDWMP/ArHQWjYBSMghEKAPG+UWasZtl/AAAAAElFTkSuQmCC","orcid":"","institution":"Guru Nanak Dev University","correspondingAuthor":true,"prefix":"","firstName":"Rajdeep","middleName":"Singh","lastName":"Sohal","suffix":""},{"id":602944704,"identity":"33959e6b-67ae-46f1-9998-1ee737aacd55","order_by":2,"name":"Manbir Kaur","email":"","orcid":"","institution":"Thapar Institute of Engineering and Technology","correspondingAuthor":false,"prefix":"","firstName":"Manbir","middleName":"","lastName":"Kaur","suffix":""},{"id":602944706,"identity":"b7782eae-3fea-4dd6-b2ae-d7da2cb698c3","order_by":3,"name":"Satinder Kaur","email":"","orcid":"","institution":"Guru Nanak Dev University","correspondingAuthor":false,"prefix":"","firstName":"Satinder","middleName":"","lastName":"Kaur","suffix":""}],"badges":[],"createdAt":"2026-03-05 18:08:51","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9043295/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9043295/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105257385,"identity":"45449453-1d36-4063-848b-557b3bacaee6","added_by":"auto","created_at":"2026-03-24 05:10:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1353567,"visible":true,"origin":"","legend":"","description":"","filename":"paper17tabla.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9043295/v1_covered_d87f2b5f-8d2c-4717-980f-e4558eca4a69.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Acoustic Feature Synergy and Self-Supervised Learning for Robust Tabla Stroke Classification","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":"tabla stroke classification, multidomain feature extraction, handcrafted features, self-supervised learning, ANOVA feature selection","lastPublishedDoi":"10.21203/rs.3.rs-9043295/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9043295/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate and robust automatic classification of tabla strokes is essential for music information retrieval and performance analysis, yet remains challenging due to complex timbral structures and subtle acoustic variability across stroke categories. To address this challenge, we propose a robust tabla stroke classification framework that integrates multidomain handcrafted features, spanning spectral, temporal, cepstral, and perceptual descriptors together with self-supervised learning (SSL) representation derived from a newly developed, manually annotated tabla dataset. This dataset is accompanied by an augmented counterpart that simulates realistic acoustic variability, enabling systematic evaluation under domain shift conditions. ANOVA F-test based feature selection is applied to retain the most discriminative attributes, and a range of machine learning classifiers are employed. Experimental results show that multidomain feature synergy significantly improves classification performance, with the Hybrid-8 configuration achieving up to 97.56% accuracy under in-domain evaluation, while SSL representation exhibits superior cross-domain robustness, attaining 94.07% accuracy when trained on original data and tested on augmented data. While handcrafted multidomain features yield near-ceiling accuracy in controlled settings, SSL representation provides stronger resilience to acoustic variability. These findings reveal a trade-off between peak discriminative performance and cross-domain generalization, highlighting the complementary strengths of handcrafted features and SSL representation for developing robust and generalizable tabla stroke classification system.\u003c/p\u003e","manuscriptTitle":"Acoustic Feature Synergy and Self-Supervised Learning for Robust Tabla Stroke Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-24 05:09:14","doi":"10.21203/rs.3.rs-9043295/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":"0a85aa46-4fe8-4ab6-9b43-7d10f5eff23f","owner":[],"postedDate":"March 24th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-24T05:09:14+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-24 05:09:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9043295","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9043295","identity":"rs-9043295","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}