WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion

WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion | 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 WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion Kyungdeuk Ko, Donghyeon kim, Kyungseok Oh, Hanseok Ko This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3180016/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 May, 2024 Read the published version in Neural Processing Letters → Version 1 posted 8 You are reading this latest preprint version Abstract Voice conversion (VC) is a task for changing the speech of a source speaker to the target voice style while preserving linguistic information of the source speech. Existing VC methods require a separate vocoder because they output mel-spectrogram. Therefore, the VC performance varies depending on the vocoder performance, and noisy speech can be generated due to problems such as train-test mismatch. In this paper, we propose a speech and fundamental frequency consistent raw audio voice conversion method called WaveVC. WaveVC does not require a separate vocoder because it performs VC directly on raw audio and is unaffected by vocoder performance. In addition, WaveVC uses speech loss and F0 loss to preserve content information and generate F0 consistent results. WaveVC shows high performance in both many-to-many VC and any-to-any VC, and the converted samples are available online. Voice conversion adversarial training deep learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 May, 2024 Read the published version in Neural Processing Letters → Version 1 posted Editorial decision: Major revision 31 Oct, 2023 Reviews received at journal 29 Sep, 2023 Reviewers agreed at journal 15 Aug, 2023 Reviewers agreed at journal 25 Jul, 2023 Reviewers invited by journal 24 Jul, 2023 Editor assigned by journal 18 Jul, 2023 Submission checks completed at journal 18 Jul, 2023 First submitted to journal 18 Jul, 2023 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-3180016","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":219583466,"identity":"fe5e0103-9c1e-4d6c-914c-2bbe39bf8b33","order_by":0,"name":"Kyungdeuk Ko","email":"","orcid":"","institution":"Korea University","correspondingAuthor":false,"prefix":"","firstName":"Kyungdeuk","middleName":"","lastName":"Ko","suffix":""},{"id":219583467,"identity":"9eff8b88-8e03-43ec-bc55-f3f0b21a7d43","order_by":1,"name":"Donghyeon kim","email":"","orcid":"","institution":"Korea University","correspondingAuthor":false,"prefix":"","firstName":"Donghyeon","middleName":"","lastName":"kim","suffix":""},{"id":219583468,"identity":"bd5d083f-c305-43b4-bf02-654b7b9e76b7","order_by":2,"name":"Kyungseok Oh","email":"","orcid":"","institution":"Korea University","correspondingAuthor":false,"prefix":"","firstName":"Kyungseok","middleName":"","lastName":"Oh","suffix":""},{"id":219583469,"identity":"fd604af5-d71d-41ac-a3e5-77c5503a96ae","order_by":3,"name":"Hanseok Ko","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYBACAwY2BoYPB+D8BOK0MM4gWQszD0lazPmPJT62OWOTz89+gPHDD4a0fIJaLGekHTbOuZFmObMngVmyhyHHsoGgw26wt0nnfDhsYHAggUGagaHCgKAtBuePt0lbALXYn3/A/Js4LQfSjkkz3ADaIpHABrQlhwgtN9KSDXvOpBlI3HjYZtljkEaMw44ZPvhxzMaAvz/58I0fFcmEtSABxgZQNI2CUTAKRsEooAYAAKtnOkWhxiSaAAAAAElFTkSuQmCC","orcid":"","institution":"Korea University","correspondingAuthor":true,"prefix":"","firstName":"Hanseok","middleName":"","lastName":"Ko","suffix":""}],"badges":[],"createdAt":"2023-07-18 04:59:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3180016/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3180016/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11063-024-11613-0","type":"published","date":"2024-05-08T04:01:09+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":56140461,"identity":"e207a69c-5fd9-4c2f-8628-2acfcc89eb7a","added_by":"auto","created_at":"2024-05-09 04:27:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":485157,"visible":true,"origin":"","legend":"","description":"","filename":"WaveVC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3180016/v1_covered_7baa2fdb-8da6-4358-a6c4-0a96bf946692.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion","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":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Voice conversion, adversarial training, deep learning","lastPublishedDoi":"10.21203/rs.3.rs-3180016/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3180016/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\nVoice conversion (VC) is a task for changing the speech of a source speaker to the target voice style while preserving linguistic information of the source speech. Existing VC methods require a separate vocoder because they output mel-spectrogram. Therefore, the VC performance varies depending on the vocoder performance, and noisy speech can be generated due to problems such as train-test mismatch. In this paper, we propose a speech and fundamental frequency consistent raw audio voice conversion method called WaveVC. WaveVC does not require a separate vocoder because it performs VC directly on raw audio and is unaffected by vocoder performance. In addition, WaveVC uses speech loss and F0 loss to preserve content information and generate F0 consistent results. WaveVC shows high performance in both many-to-many VC and any-to-any VC, and the converted samples are available online.\n","manuscriptTitle":"WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-07-21 05:57:20","doi":"10.21203/rs.3.rs-3180016/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-10-31T09:10:44+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-09-29T17:26:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"95271c6a-da6e-48f6-8fec-ece342e48ff6","date":"2023-08-15T17:49:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7c276e30-9bd6-48c4-b119-425c997d629f","date":"2023-07-25T14:04:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-07-24T19:48:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-07-18T13:09:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-07-18T13:09:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Neural Processing Letters","date":"2023-07-18T04:55:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a249295d-e7f0-4df8-b61a-31c48179a82f","owner":[],"postedDate":"July 21st, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-05-09T04:01:09+00:00","versionOfRecord":{"articleIdentity":"rs-3180016","link":"https://doi.org/10.1007/s11063-024-11613-0","journal":{"identity":"neural-processing-letters","isVorOnly":false,"title":"Neural Processing Letters"},"publishedOn":"2024-05-08 04:01:09","publishedOnDateReadable":"May 8th, 2024"},"versionCreatedAt":"2023-07-21 05:57:20","video":"","vorDoi":"10.1007/s11063-024-11613-0","vorDoiUrl":"https://doi.org/10.1007/s11063-024-11613-0","workflowStages":[]},"version":"v1","identity":"rs-3180016","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3180016","identity":"rs-3180016","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}