An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length | 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 An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length NALLABALA NAVEENKUMAR This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3974637/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 In this research, it is suggested that a hybrid architecture for text-to-speech, which is named it as Efficient Speech Synthesizer. ESS optimizes all the parameters through a consistent, end-to-end training process that enables fast and efficient speech synthesis of exceptional quality without depending on the length of the sentences. ESS is powered by combining feed-forward approaches like Variational Auto Encoders and Linear Predictive Coding techniques. These techniques give monotonic limitations to the sequence alignment with almost no increase in computation. The present research focuses on TTS model with low complexity, low latency which is suitable for both high-end and low-end computational devices like IoT and smart Phones. Efficient Speech Synthesizer Non-autoregressive Autoregressive Monotonic Alignment Linear Predictive Coding Variational Auto Encoder 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-3974637","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":276989770,"identity":"9561d364-de30-45e2-b03d-66e9eca4f90c","order_by":0,"name":"NALLABALA NAVEENKUMAR","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYHAD5gNAQkKGFC1sCSAtPKRo4TEAkwTVmbOfMXzwcccde4MbOZ9f3aix4GFgP3x0Az4tlj05xoYzzzxL3HAjd5t1zjGgw3jS0m7g02JwIC1NmrftcILkjNxtxjlsQC0SPGb4tZx/lv77b9the8kZOc+Mc/4Ro+VG8jFmxrbDjP0SOcyPc9uI0vL4sGRv2+HEfp5nZsy5fRI8bAT9cj6x8cNPoMPY2JMff875VifHz374GF4tyIBNAkwSqxwEmD+QonoUjIJRMApGDgAAvyVIjllNp8AAAAAASUVORK5CYII=","orcid":"","institution":"Jawaharlal Nehru Technological University Anantapur","correspondingAuthor":true,"prefix":"","firstName":"NALLABALA","middleName":"","lastName":"NAVEENKUMAR","suffix":""}],"badges":[],"createdAt":"2024-02-21 05:33:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3974637/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3974637/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57030402,"identity":"40e2fd05-dd46-41d4-a159-68ef19ca5242","added_by":"auto","created_at":"2024-05-23 16:34:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":744274,"visible":true,"origin":"","legend":"","description":"","filename":"PtoP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3974637/v1_covered_15a75ae0-858f-4a7e-9056-32901c08d414.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE \u0026 LPC-net with independent sentence length","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":"Efficient Speech Synthesizer, Non-autoregressive, Autoregressive, Monotonic Alignment, Linear Predictive Coding, Variational Auto Encoder","lastPublishedDoi":"10.21203/rs.3.rs-3974637/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3974637/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this research, it is suggested that a hybrid architecture for text-to-speech, which is named it as Efficient Speech Synthesizer. ESS optimizes all the parameters through a consistent, end-to-end training process that enables fast and efficient speech synthesis of exceptional quality without depending on the length of the sentences. ESS is powered by combining feed-forward approaches like Variational Auto Encoders and Linear Predictive Coding techniques. These techniques give monotonic limitations to the sequence alignment with almost no increase in computation. The present research focuses on TTS model with low complexity, low latency which is suitable for both high-end and low-end computational devices like IoT and smart Phones.\u003c/p\u003e","manuscriptTitle":"An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE \u0026amp; LPC-net with independent sentence length","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-11 05:17:20","doi":"10.21203/rs.3.rs-3974637/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":"6eb8fc7e-79da-4780-bf12-254416df6b24","owner":[],"postedDate":"March 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-05-23T16:25:59+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-11 05:17:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3974637","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3974637","identity":"rs-3974637","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}