GD-Conformer: a Conformer-based gated dense encoder-decoder for monaural speech enhancement

GD-Conformer: a Conformer-based gated dense encoder-decoder for monaural speech enhancement | 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 GD-Conformer: a Conformer-based gated dense encoder-decoder for monaural speech enhancement Gengzangcuomao FNU, Heming Huang, Feipeng Da This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6111294/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Jun, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 11 You are reading this latest preprint version Abstract Speech enhancement improves speech quality by mitigating noise, dereverberation, and echo. Existing methods struggle with amplitude-phase compensation, capturing temporal-frequency features, and high complexity. To address these issues, a gated dense encoder-decoder architecture with a two-stage Conformer, abbreviated as GD-Conformer, is proposed. It integrates a gated dense module, a two-stage residual Conformer module, a mask decoder and a complex decoder. The gated dense module consists of two parts: a dilated dense convolution and a gated convolution, where the former captures both global and local dependencies features, while the latter refines these distinct features accordingly. The two-stage residual Conformer focuses on the time-frequency dependence of speech, it also reduces the computational complexity. The mask decoder and the complex decoder restore spectral resolution while preserving speech fidelity. The outcomes of experiments conducted on the public dataset VoiceBank+DEMAND and DNS Challenge 2020 demonstrate that, compared with those state-of-the-art methods, the proposed GD-Conformer achieves comparable performance in terms of denoising and generalization with fewer parameters and lower computation complexity. Speech enhancement encoder-decoder architecture magnitude and complex spectrogram two-stage residual Conformer network gated dense network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Jun, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 04 May, 2025 Reviews received at journal 04 May, 2025 Reviews received at journal 28 Apr, 2025 Reviews received at journal 24 Apr, 2025 Reviewers agreed at journal 13 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers invited by journal 12 Apr, 2025 Submission checks completed at journal 01 Apr, 2025 First submitted to journal 26 Mar, 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-6111294","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":448992307,"identity":"0f1a6b8d-ca99-42da-976d-170f112f3c1f","order_by":0,"name":"Gengzangcuomao FNU","email":"","orcid":"","institution":"Qinghai Normal University","correspondingAuthor":false,"prefix":"","firstName":"Gengzangcuomao","middleName":"","lastName":"FNU","suffix":""},{"id":448992312,"identity":"92ae36b4-6f64-41c8-b9d3-16e4515f6732","order_by":1,"name":"Heming Huang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIiWNgGAWjYBACNmbmAwckKmx4+NmbDxCnhY+9LfGAxZk0OcmeYwnEaZHjOWN8oLLtsLHBjBwDIh0mkWBw4MaZw4kbeM58vPGGwU5Ot4GwloSDMyrSE7ez9262nMOQbGx2gLCWA4clzlgn7uw5u02ah+FA4jbCWhIbDv9tY07ccCPnGZFaeA4zHJBsczY2uJHDRqQW9jaGAxKQQDa2nGNAhF/km/k/f4BG5cMbbyrs5AhqQQESPERGDbIWUnWMglEwCkbBiAAAlXBIYfVa27wAAAAASUVORK5CYII=","orcid":"","institution":"Qinghai Normal University","correspondingAuthor":true,"prefix":"","firstName":"Heming","middleName":"","lastName":"Huang","suffix":""},{"id":448992313,"identity":"7baba24d-4c5a-4c42-b1ec-a46e23a31fa6","order_by":2,"name":"Feipeng Da","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Feipeng","middleName":"","lastName":"Da","suffix":""}],"badges":[],"createdAt":"2025-02-26 08:38:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6111294/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6111294/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04400-4","type":"published","date":"2025-06-27T15:57:09+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":85686112,"identity":"2afcf9c7-5498-49aa-976b-0aeace3f4467","added_by":"auto","created_at":"2025-06-30 16:03:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":445162,"visible":true,"origin":"","legend":"","description":"","filename":"Article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6111294/v1_covered_d840cf01-fc33-4434-bce7-98d8b88c22ad.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GD-Conformer: a Conformer-based gated dense encoder-decoder for monaural speech enhancement","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Speech enhancement, encoder-decoder architecture, magnitude and complex spectrogram, two-stage residual Conformer network, gated dense network","lastPublishedDoi":"10.21203/rs.3.rs-6111294/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6111294/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSpeech enhancement improves speech quality by mitigating noise, dereverberation, and echo. Existing methods struggle with amplitude-phase compensation, capturing temporal-frequency features, and high complexity. To address these issues, a gated dense encoder-decoder architecture with a two-stage Conformer, abbreviated as GD-Conformer, is proposed. It integrates a gated dense module, a two-stage residual Conformer module, a mask decoder and a complex decoder. The gated dense module consists of two parts: a dilated dense convolution and a gated convolution, where the former captures both global and local dependencies features, while the latter refines these distinct features accordingly. The two-stage residual Conformer focuses on the time-frequency dependence of speech, it also reduces the computational complexity. The mask decoder and the complex decoder restore spectral resolution while preserving speech fidelity. The outcomes of experiments conducted on the public dataset VoiceBank+DEMAND and DNS Challenge 2020 demonstrate that, compared with those state-of-the-art methods, the proposed GD-Conformer achieves comparable performance in terms of denoising and generalization with fewer parameters and lower computation complexity.\u003c/p\u003e","manuscriptTitle":"GD-Conformer: a Conformer-based gated dense encoder-decoder for monaural speech enhancement","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-29 10:14:07","doi":"10.21203/rs.3.rs-6111294/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-04T20:33:19+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-04T08:16:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-28T09:23:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-24T15:04:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"74711049963401534441068929205982418725","date":"2025-04-13T06:43:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59386415085439271230290830381391061136","date":"2025-04-12T17:51:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"112176907578438154413852598867235476842","date":"2025-04-12T17:22:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247649657253529823867537694360785570171","date":"2025-04-12T17:06:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-12T16:57:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-01T16:39:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-03-26T08:32:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"fd865e56-9c54-461a-826e-4fd7369656ec","owner":[],"postedDate":"April 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-30T15:59:09+00:00","versionOfRecord":{"articleIdentity":"rs-6111294","link":"https://doi.org/10.1007/s11760-025-04400-4","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-06-27 15:57:09","publishedOnDateReadable":"June 27th, 2025"},"versionCreatedAt":"2025-04-29 10:14:07","video":"","vorDoi":"10.1007/s11760-025-04400-4","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04400-4","workflowStages":[]},"version":"v1","identity":"rs-6111294","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6111294","identity":"rs-6111294","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}