Experimental investigation of Deep Neural Networks inspired Supervised and Semi- Supervised Cocktail Party Problem based Speech Separation

Experimental investigation of Deep Neural Networks inspired Supervised and Semi- Supervised Cocktail Party Problem based Speech Separation | 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 Experimental investigation of Deep Neural Networks inspired Supervised and Semi- Supervised Cocktail Party Problem based Speech Separation Jaipreet Kour Wazir, Javaid A Sheikh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8170302/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Multiple speakers while communicating simultaneously with background noise is a difficult problem to address particularly in the modern multimedia world. Cocktail party problem (CPP), basically used to identify the target speaker from multiple speakers is the standard approach identified by several researchers. Traditional Speech separation processing methods such as non-negative matrix factorization (NMF) and Computational Auditory Scene Analysis (CASA) for single-channel processing and for multi-channel processing blind source separation (BSS), independent component analysis (ICA) is applied to CCP to address the issue. Speech separation using deep neural networks is a great area of research with the potential to significantly improve the area of speech processing. This work introduces a novel approach for speech separation processing in a single channel and to separate the speakers from a mixed speech signal. In this work, two approaches are proposed: one based on supervised learning and the other on unsupervised learning, both the approaches are compared based on perceptual evaluation of speech quality (PESQ), source-to- noise ratio (SI-SNRi), scale-invariant signal-to-distortion ratio improvement (SDRi) and signal to distortion ratio (STOI). This experiment is conducted on the TIMIT dataset. The data is mixed at SNRs ranging from − 5 dB to 5dB. In the proposed work the results have been analyzed using both objective and subjective analysis which gives efficacy of the work. Speech separation cocktail party problem Deep learning TIMIT data set Deep Neural Networks Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 04 Dec, 2025 Editor assigned by journal 28 Nov, 2025 Submission checks completed at journal 28 Nov, 2025 First submitted to journal 21 Nov, 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-8170302","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":556131831,"identity":"8c3df3b6-ee3a-46f8-b830-4613c0c0881b","order_by":0,"name":"Jaipreet Kour Wazir","email":"","orcid":"","institution":"University of Kashmir","correspondingAuthor":false,"prefix":"","firstName":"Jaipreet","middleName":"Kour","lastName":"Wazir","suffix":""},{"id":556131833,"identity":"35c7e26c-2977-4577-bc3a-1c3646fce101","order_by":1,"name":"Javaid A Sheikh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABA0lEQVRIiWNgGAWjYDACCQaGg40NbEAWY4PEBwYGAwYwNiBSi+QMYrUwNjZA2NI8cC14gPzs5oMHZ+7gkzc4frjxtm2bjTEDe/M2CYaCOzi1GNw5lnBw4xk2ww1nEputc9vSzBh4jpVJMBg8w61FIsfg4MM2NsaZDYlt0rlth20YJHLMgFoO43bYjPwPIC32M/sftklbgrTIv8GvheFGDsPBjW1sif0SQFsY2w6bMUjw4NdicCPN4ODMNrbkfomHzZY959KM2XjSii0S8Dos+fHH3rZjtm386Q9v/CizMexnP7zxxoc/eBwGAccQTFCsMiQQ0sDAUENYySgYBaNgFIxcAABOVFdbv71bEgAAAABJRU5ErkJggg==","orcid":"","institution":"University of Kashmir","correspondingAuthor":true,"prefix":"","firstName":"Javaid","middleName":"A","lastName":"Sheikh","suffix":""}],"badges":[],"createdAt":"2025-11-21 06:38:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8170302/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8170302/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97644026,"identity":"e31118fe-d6d8-4fab-8b39-968c71103c99","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":637648,"visible":true,"origin":"","legend":"","description":"","filename":"CPP.docx","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/75266e5d5c2b2274638e31f9.docx"},{"id":97644024,"identity":"6ed9a78c-c0ea-4c78-aaa3-3e1340a64ba0","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4092,"visible":true,"origin":"","legend":"","description":"","filename":"259b56d8423a44a2a13df0d6346dd588.json","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/5af42656905716dc320a83b6.json"},{"id":97644025,"identity":"88bf2d3e-2080-4540-be36-2c7a6bbb1479","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74481,"visible":true,"origin":"","legend":"","description":"","filename":"259b56d8423a44a2a13df0d6346dd5881enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/7c164de1c2bbc0684fb869a9.xml"},{"id":97673754,"identity":"b88f68dc-9e2a-4358-969f-7dacc128a250","added_by":"auto","created_at":"2025-12-08 09:41:19","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":137267,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/e71af2e2cf6b9de82831d4d1.png"},{"id":97644035,"identity":"490d9c61-834d-47b5-a429-d82273c6dbbe","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142575,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/4316705c4cb3e1c6fb7492e1.png"},{"id":97644027,"identity":"f515020f-e4d9-402f-88d4-513611f139d8","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41186,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/ced0ff2bc2205b9ed4f60827.png"},{"id":97673994,"identity":"15f371c8-3ffb-4757-9f72-e0ec2d6eb441","added_by":"auto","created_at":"2025-12-08 09:42:05","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174750,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/fe7e9439cb1ee9bc2d0d8c9c.png"},{"id":97673780,"identity":"69d5b59a-e4ff-421a-8d29-8004c5aef6a3","added_by":"auto","created_at":"2025-12-08 09:41:23","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":173110,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/29bae6fcbe0574187e6ddeea.jpeg"},{"id":97644030,"identity":"5710191a-da35-4994-8edb-c79fa53ba11a","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56996,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/f3079988d0c17912f0b32386.png"},{"id":97644039,"identity":"99353864-300f-4101-9db8-c2ff5bde07ed","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14911,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/a91123544172d5bced796d5d.png"},{"id":97674209,"identity":"dfc1bd96-91c7-49e1-ac0e-f27a3f249c20","added_by":"auto","created_at":"2025-12-08 09:42:38","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":272970,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/d3e68c2b83e26e360c149874.jpeg"},{"id":97644031,"identity":"1a770800-db80-4581-84a7-d0c28b82d546","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35313,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/5242aeb3936ac942427dcd3f.png"},{"id":97673524,"identity":"00dd81f8-f94d-4ae2-8274-1b1d4676c769","added_by":"auto","created_at":"2025-12-08 09:40:30","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24932,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/d7ab4a4b81324bfebc22c956.png"},{"id":97644034,"identity":"16c1e6c7-0d0d-457d-ab2c-9405539876a2","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17350,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/ff265b7316c73b4f2b4409b8.png"},{"id":97644043,"identity":"7d0cbf63-d59e-45e8-aee4-d7cbaf6005d7","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37677,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/b4d2b83962dd6e519eceb6ba.png"},{"id":97644041,"identity":"510037b1-265f-497b-a831-415653e35d14","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46358,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/001c4ad318d9c0a83d9230dc.png"},{"id":97644032,"identity":"37d44a1d-816a-4bd6-97b8-60c35d7d0e0b","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17669,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/ab86f58c731be43c68375816.png"},{"id":97673624,"identity":"3e669dcf-9216-4697-a59e-d677a4d507e9","added_by":"auto","created_at":"2025-12-08 09:40:50","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6723,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/6730f6929acae23b0a6a156e.png"},{"id":97673580,"identity":"0e965c83-1602-4332-a11c-ae2f3a882b4f","added_by":"auto","created_at":"2025-12-08 09:40:41","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50755,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/23d28e1b00509e7d38a5a183.png"},{"id":97644044,"identity":"b4c1e35b-ee51-4a3f-9738-3db791e4783b","added_by":"auto","created_at":"2025-12-08 04:18:15","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":71877,"visible":true,"origin":"","legend":"","description":"","filename":"259b56d8423a44a2a13df0d6346dd5881structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/f638493d403448c54a6364bc.xml"},{"id":97672190,"identity":"9d2263bf-658e-4ea9-aa85-eeb5c4b503d3","added_by":"auto","created_at":"2025-12-08 09:34:35","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85107,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1/27c1c085e396580df8c0f5e7.html"},{"id":97678864,"identity":"390c3ffd-8dc2-40c4-8a87-77a90f9a576b","added_by":"auto","created_at":"2025-12-08 09:56:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":757085,"visible":true,"origin":"","legend":"","description":"","filename":"CPP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8170302/v1_covered_93736a5f-2409-417f-995a-7b11db5c13f6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Experimental investigation of Deep Neural Networks inspired Supervised and Semi- Supervised Cocktail Party Problem based Speech Separation","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":"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 separation, cocktail party problem, Deep learning, TIMIT data set, Deep Neural Networks","lastPublishedDoi":"10.21203/rs.3.rs-8170302/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8170302/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMultiple speakers while communicating simultaneously with background noise is a difficult problem to address particularly in the modern multimedia world. Cocktail party problem (CPP), basically used to identify the target speaker from multiple speakers is the standard approach identified by several researchers. Traditional Speech separation processing methods such as non-negative matrix factorization (NMF) and Computational Auditory Scene Analysis (CASA) for single-channel processing and for multi-channel processing blind source separation (BSS), independent component analysis (ICA) is applied to CCP to address the issue. Speech separation using deep neural networks is a great area of research with the potential to significantly improve the area of speech processing. This work introduces a novel approach for speech separation processing in a single channel and to separate the speakers from a mixed speech signal. In this work, two approaches are proposed: one based on supervised learning and the other on unsupervised learning, both the approaches are compared based on perceptual evaluation of speech quality (PESQ), source-to- noise ratio (SI-SNRi), scale-invariant signal-to-distortion ratio improvement (SDRi) and signal to distortion ratio (STOI). This experiment is conducted on the TIMIT dataset. The data is mixed at SNRs ranging from \u0026minus;\u0026thinsp;5 dB to 5dB. In the proposed work the results have been analyzed using both objective and subjective analysis which gives efficacy of the work.\u003c/p\u003e","manuscriptTitle":"Experimental investigation of Deep Neural Networks inspired Supervised and Semi- Supervised Cocktail Party Problem based Speech Separation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-08 04:18:10","doi":"10.21203/rs.3.rs-8170302/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2025-12-04T06:09:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-28T09:22:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-28T09:21:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-11-21T06:31:23+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":"cf589844-274c-43bc-b470-1230e9b45a4c","owner":[],"postedDate":"December 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T04:18:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-08 04:18:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8170302","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8170302","identity":"rs-8170302","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}