TAC-Net:Triple Attention Contrastive Network for Speech Complex Emotion Recognition in Real-Scene

TAC-Net:Triple Attention Contrastive Network for Speech Complex Emotion Recognition in Real-Scene | 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 TAC-Net:Triple Attention Contrastive Network for Speech Complex Emotion Recognition in Real-Scene Hankiz Yilahun, Chaobo Song, Askar Hamdulla This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8807080/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Speech Emotion Recognition (SER) in real-world scenarios remains a challenging task due to uncontrolled acoustic interference and the co-occurrence of complex emotions. Existing single-label approaches often struggle to capture fine-grained emotional semantics while suppressing noise, leading to significant performance degradation in complex environments. To address this, we propose a Triple Attention Contrastive Network (TAC-Net), designed to enhance model robustness through multi-dimensional feature decoupling and reconstruction. First, we introduce a Label-wise Attention Module comprising three collaborative networks: Multi-label Attention (MLA) explicitly models the latent dependencies among emotion tags; Local-Global Attention (LGA) locates key emotional frames temporally while capturing long-range context; and Time-Frequency Attention (TFA) focuses on spectral energy distributions to mitigate channel distortion. Furthermore, a Contrastive Reconstruction-based Fusion Module is incorporated to align heterogeneous features in the latent space via contrastive learning, effectively filtering redundant noise while preserving critical emotional information. Experimental results on the large-scale M³ED and CMU-MOSEI datasets demonstrate that TAC-Net not only significantly outperforms existing unimodal baselines but also achieves competitive performance comparable to multimodal methods in handling multi-label and noisy data. Speech Emotion Recognition Multi-Label Classification Attention Mechanism Contrastive Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 03 May, 2026 Reviews received at journal 02 May, 2026 Reviews received at journal 12 Mar, 2026 Reviewers agreed at journal 11 Mar, 2026 Reviewers agreed at journal 11 Mar, 2026 Reviewers invited by journal 24 Feb, 2026 Editor assigned by journal 22 Feb, 2026 Submission checks completed at journal 20 Feb, 2026 First submitted to journal 06 Feb, 2026 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-8807080","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":596139005,"identity":"4bab5edf-3ee0-497b-aa55-5861008f7c53","order_by":0,"name":"Hankiz Yilahun","email":"","orcid":"","institution":"XinJiang University","correspondingAuthor":false,"prefix":"","firstName":"Hankiz","middleName":"","lastName":"Yilahun","suffix":""},{"id":596139006,"identity":"6bf0e6f4-2325-422e-8552-8df2f12bc5b4","order_by":1,"name":"Chaobo Song","email":"data:image/png;base64,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","orcid":"","institution":"XinJiang University","correspondingAuthor":true,"prefix":"","firstName":"Chaobo","middleName":"","lastName":"Song","suffix":""},{"id":596139007,"identity":"09b7b47c-8ba3-4a72-a783-44544a00d5ba","order_by":2,"name":"Askar Hamdulla","email":"","orcid":"","institution":"XinJiang University","correspondingAuthor":false,"prefix":"","firstName":"Askar","middleName":"","lastName":"Hamdulla","suffix":""}],"badges":[],"createdAt":"2026-02-06 12:27:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8807080/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8807080/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103469040,"identity":"c458c3b8-6289-470c-9c6d-1a27ec12e47f","added_by":"auto","created_at":"2026-02-26 05:10:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1649626,"visible":true,"origin":"","legend":"","description":"","filename":"TACNetTripleAttentionContrastiveNetworkforSpeechComplexEmotionRecognitioninRealScene1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8807080/v1_covered_8f53d0a6-3fdd-49b0-a3d5-57a42e27701c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"TAC-Net:Triple Attention Contrastive Network for Speech Complex Emotion Recognition in Real-Scene","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Speech Emotion Recognition, Multi-Label Classification, Attention Mechanism, Contrastive Learning","lastPublishedDoi":"10.21203/rs.3.rs-8807080/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8807080/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSpeech Emotion Recognition (SER) in real-world scenarios remains a challenging task due to uncontrolled acoustic interference and the co-occurrence of complex emotions. Existing single-label approaches often struggle to capture fine-grained emotional semantics while suppressing noise, leading to significant performance degradation in complex environments. To address this, we propose a Triple Attention Contrastive Network (TAC-Net), designed to enhance model robustness through multi-dimensional feature decoupling and reconstruction. First, we introduce a Label-wise Attention Module comprising three collaborative networks: Multi-label Attention (MLA) explicitly models the latent dependencies among emotion tags; Local-Global Attention (LGA) locates key emotional frames temporally while capturing long-range context; and Time-Frequency Attention (TFA) focuses on spectral energy distributions to mitigate channel distortion. Furthermore, a Contrastive Reconstruction-based Fusion Module is incorporated to align heterogeneous features in the latent space via contrastive learning, effectively filtering redundant noise while preserving critical emotional information. Experimental results on the large-scale M\u0026sup3;ED and CMU-MOSEI datasets demonstrate that TAC-Net not only significantly outperforms existing unimodal baselines but also achieves competitive performance comparable to multimodal methods in handling multi-label and noisy data.\u003c/p\u003e","manuscriptTitle":"TAC-Net:Triple Attention Contrastive Network for Speech Complex Emotion Recognition in Real-Scene","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-26 05:09:48","doi":"10.21203/rs.3.rs-8807080/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-04T00:46:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T17:22:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-12T04:06:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"317040247447545724200676311972120710176","date":"2026-03-12T03:14:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"142311220467577430165718198658454035811","date":"2026-03-11T16:01:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-24T08:18:49+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-23T04:36:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-20T10:01:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2026-02-06T11:53:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2ff44ffd-5223-40e6-a56a-fe0b2ae9c43f","owner":[],"postedDate":"February 26th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-04T00:46:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T17:22:15+00:00","index":19,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-04T00:53:49+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-26 05:09:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8807080","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8807080","identity":"rs-8807080","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}