BnVITS: A Voice Cloning Approach for Single Speaker Text-to-Speech | 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 BnVITS: A Voice Cloning Approach for Single Speaker Text-to-Speech Udoy Das, Md. Saiful Islam, Hasan Murad, Muhammad Ibrahim Khan, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6530449/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Although significant progress has been made in voice cloning and text-to-speech (TTS) models, especially in generating natural-sounding speech, low-resource languages such as Bangla (Bn) and other languages remain nearly unexplored. Despite recent advancements, TTS systems for the Bangla language still encounter difficulties due to the intricate phonology and morphology. Furthermore, no previous work has been done on voice cloning for Bangla. To address the research gap, we provide a voice cloning method that uses the limited amount of speech data possible to build a TTS system for Bangla. Additionally, we introduce PYBANGLA, a text normalization tool created especially for Bangla language processing. Voice cloning can be accomplished by honing the top-performing TTS models with just a few target speaker samples. Both subjective and objective evaluation metrics have been conducted to assess the system, and the results show that our BnVITS model performs better than the earlier Bangla TTS model. This approach opens up new opportunities for individualized voice technology by paving the road for more efficient Bangla TTS approaches in terms of speech data. Voice Cloning Text-to-Speech (TTS) Bangla (Bn) PYBANGLA Bn VITS Model Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 29 May, 2025 Reviews received at journal 23 May, 2025 Reviews received at journal 22 May, 2025 Reviewers agreed at journal 22 May, 2025 Reviews received at journal 13 May, 2025 Reviewers agreed at journal 12 May, 2025 Reviewers agreed at journal 11 May, 2025 Reviewers invited by journal 07 May, 2025 Editor assigned by journal 05 May, 2025 Submission checks completed at journal 05 May, 2025 First submitted to journal 25 Apr, 2025 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-6530449","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":455467322,"identity":"15f3f17f-cc97-483e-ad80-b9168d32f63f","order_by":0,"name":"Udoy Das","email":"data:image/png;base64,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","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":true,"prefix":"","firstName":"Udoy","middleName":"","lastName":"Das","suffix":""},{"id":455467324,"identity":"e7a9db24-bbe6-474b-bd04-6d62f43b72c5","order_by":1,"name":"Md. Saiful Islam","email":"","orcid":"","institution":"Hishab Technologies Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Md.","middleName":"Saiful","lastName":"Islam","suffix":""},{"id":455467326,"identity":"315a6a31-3095-47f8-8ab5-d705d98f9911","order_by":2,"name":"Hasan Murad","email":"","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Hasan","middleName":"","lastName":"Murad","suffix":""},{"id":455467327,"identity":"7a168101-c815-47c0-892a-f28dbac35a79","order_by":3,"name":"Muhammad Ibrahim Khan","email":"","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Ibrahim","lastName":"Khan","suffix":""},{"id":455467328,"identity":"717b039a-8362-4cf7-9df4-ba95f8c31260","order_by":4,"name":"Mehadi Hasan Menon","email":"","orcid":"","institution":"Hishab Technologies Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Mehadi","middleName":"Hasan","lastName":"Menon","suffix":""},{"id":455467330,"identity":"01f47d44-9edf-4af5-a56e-45c19ae5762b","order_by":5,"name":"Tareq Muntasir","email":"","orcid":"","institution":"Hishab Technologies Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Tareq","middleName":"","lastName":"Muntasir","suffix":""}],"badges":[],"createdAt":"2025-04-25 16:08:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6530449/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6530449/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82600456,"identity":"3cb9b2b8-27b7-4a5f-9780-c694474bc486","added_by":"auto","created_at":"2025-05-13 09:32:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":502200,"visible":true,"origin":"","legend":"","description":"","filename":"BnVITSManuscriptrevised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6530449/v1_covered_0b3dbb96-f26e-44f6-8c5e-817f8006568d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"BnVITS: A Voice Cloning Approach for Single Speaker Text-to-Speech","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"
[email protected]","identity":"discover-applied-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Applied Sciences](https://link.springer.com/journal/42452)","snPcode":"42452","submissionUrl":"https://submission.springernature.com/new-submission/42452/3","title":"Discover Applied Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Voice Cloning, Text-to-Speech (TTS), Bangla (Bn), PYBANGLA, Bn VITS Model","lastPublishedDoi":"10.21203/rs.3.rs-6530449/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6530449/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Although significant progress has been made in voice cloning and text-to-speech (TTS) models, especially in generating natural-sounding speech, low-resource languages such as Bangla (Bn) and other languages remain nearly unexplored. Despite recent advancements, TTS systems for the Bangla language still encounter difficulties due to the intricate phonology and morphology. Furthermore, no previous work has been done on voice cloning for Bangla. To address the research gap, we provide a voice cloning method that uses the limited amount of speech data possible to build a TTS system for Bangla. Additionally, we introduce PYBANGLA, a text normalization tool created especially for Bangla language processing. Voice cloning can be accomplished by honing the top-performing TTS models with just a few target speaker samples. Both subjective and objective evaluation metrics have been conducted to assess the system, and the results show that our BnVITS model performs better than the earlier Bangla TTS model. This approach opens up new opportunities for individualized voice technology by paving the road for more efficient Bangla TTS approaches in terms of speech data.","manuscriptTitle":"BnVITS: A Voice Cloning Approach for Single Speaker Text-to-Speech","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-13 09:24:48","doi":"10.21203/rs.3.rs-6530449/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-29T06:26:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-23T15:46:59+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-22T15:26:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"26410177274756925329830860143850475586","date":"2025-05-22T14:53:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-13T23:14:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"274121078622160601264908284689264526215","date":"2025-05-12T15:17:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"98544606712730643082896541570414089188","date":"2025-05-12T03:45:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-07T21:48:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-05T12:55:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-05T12:50:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Applied Sciences","date":"2025-04-25T15:55:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"discover-applied-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Applied Sciences](https://link.springer.com/journal/42452)","snPcode":"42452","submissionUrl":"https://submission.springernature.com/new-submission/42452/3","title":"Discover Applied Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ebd672ab-3b90-4fbb-9410-53ebf0d1d07a","owner":[],"postedDate":"May 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-06-17T06:38:54+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-13 09:24:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6530449","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6530449","identity":"rs-6530449","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","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.