{"id":"https://openalex.org/W4416381361","doi":"https://doi.org/10.1109/access.2025.3632214","title":"Retraining-Free Pruning Text-to-Speech Synthesis Model for Speaker Cloning","display_name":"Retraining-Free Pruning Text-to-Speech Synthesis Model for Speaker Cloning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416381361","doi":"https://doi.org/10.1109/access.2025.3632214"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3632214","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3632214","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3632214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007024435","display_name":"Ali Raheem Mandeel","orcid":"https://orcid.org/0000-0003-4188-2196"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Ali Raheem Mandeel","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-4188-2196","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045366957","display_name":"Tamara Z. Fadhil","orcid":"https://orcid.org/0000-0002-3685-7546"},"institutions":[{"id":"https://openalex.org/I4210119257","display_name":"University of Information Technology and Communications","ror":"https://ror.org/028h0pd91","country_code":"IQ","type":"education","lineage":["https://openalex.org/I4210119257"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Tamara Z. Fadhil","raw_affiliation_strings":["College of Engineering, University of Information Technology and Communications, Baghdad, Iraq"],"raw_orcid":"https://orcid.org/0000-0002-3685-7546","affiliations":[{"raw_affiliation_string":"College of Engineering, University of Information Technology and Communications, Baghdad, Iraq","institution_ids":["https://openalex.org/I4210119257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033058323","display_name":"Mohammed Hamzah Abed","orcid":"https://orcid.org/0000-0003-4780-4252"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Mohammed Hamzah Alsalihi","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-4780-4252","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086670617","display_name":"Mohammed Salah Al-Radhi","orcid":"https://orcid.org/0000-0003-3094-6916"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Mohammed Salah Al-Radhi","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-3094-6916","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e9za N\u00e9meth","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-2311-4858","affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16877828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"193603","last_page":"193615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8482999801635742,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8482999801635742,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.04390000179409981,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.016499999910593033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8935999870300293},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8113999962806702},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.661899983882904},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.611299991607666},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5066999793052673},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4115999937057495},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3596999943256378},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.35350000858306885}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8935999870300293},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8113999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968999743461609},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.661899983882904},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5712000131607056},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3632214","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3632214","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ee417cdadc344bf087f24496ca5f5c03","is_oa":true,"landing_page_url":"https://doaj.org/article/ee417cdadc344bf087f24496ca5f5c03","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 193603-193615 (2025)","raw_type":"article"},{"id":"pmh:oai:zenodo.org:17661259","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ACCESS.2025.3632214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, 13, 13, (2025-11-12)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3632214","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3632214","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"text-to-speech":[1],"(TTS)":[2],"synthesis":[3,242],"models":[4,77,231],"can":[5],"produce":[6],"highly":[7],"natural":[8],"speech":[9,109,241,265],"by":[10,56,92,96],"drawing":[11],"on":[12,152],"large-scale":[13],"pretraining":[14],"with":[15,34,206,256,264],"extensive":[16],"datasets":[17],"and":[18,48,58,111,141,158,170,210],"subsequent":[19],"adaptation":[20,115],"to":[21,69,88,105,116,173,234],"specific":[22],"target":[23],"speakers,":[24],"such":[25,135],"as":[26,30,136],"voice":[27,79],"cloning.":[28,80],"However,":[29],"model":[31,166,177,188],"sizes":[32],"grow":[33],"increasingly":[35],"comprehensive":[36],"pretraining,":[37],"fine-tuning":[38],"all":[39,133],"parameters":[40,91],"for":[41,65,78,113,259,262],"each":[42],"speaker":[43],"becomes":[44],"both":[45],"computationally":[46],"demanding":[47],"resource-intensive.":[49],"In":[50],"this":[51,247],"study,":[52],"we":[53],"adapted":[54],"Pruning":[55],"Weights":[57],"Activations":[59],"(Wanda),":[60],"a":[61,83,192,202],"technique":[62],"initially":[63],"developed":[64],"large":[66],"language":[67],"models,":[68],"reduce":[70],"the":[71,107,163,174,180,207,219,236,250],"parameter":[72],"footprint":[73],"of":[74,198,204,216,246,252],"pretrained":[75],"TTS":[76,122,165,176,187,230,254],"Wanda":[81,209],"leverages":[82],"simple":[84],"yet":[85],"effective":[86],"metric":[87],"prune":[89],"redundant":[90],"multiplying":[93],"weight":[94],"magnitudes":[95],"input":[97],"activation":[98],"norms.":[99],"It":[100],"does":[101],"not":[102],"require":[103],"post-retraining":[104],"preserve":[106],"synthesized":[108],"quality":[110],"allows":[112],"efficient":[114],"cloned":[117],"voices.":[118],"Our":[119,184],"proposed":[120,185],"pruning":[121,126,182,214],"method":[123],"uses":[124],"two":[125],"schemes,":[127],"<italic":[128,142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129,143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">structured":[130],"Wanda</i>":[131,145],"(removes":[132,146],"units,":[134],"neurons,":[137],"filters,":[138],"or":[139,148,154],"channels)":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">unstructured":[144],"weights":[147],"individual":[149],"connections":[150],"based":[151],"magnitude":[153],"significance":[155],"scores).":[156],"Subjective":[157],"objective":[159],"evaluations":[160],"showed":[161],"that":[162,225],"pruned":[164,186],"exhibited":[167],"promising":[168],"results":[169],"was":[171],"comparable":[172],"baseline":[175],"(non-pruned)":[178],"at":[179],"one-quarter":[181,205],"level.":[183],"subjectively":[189],"achieved":[190],"only":[191],"relatively":[193],"small":[194],"decline":[195],"in":[196,201,212,239],"naturalness":[197],"approximately":[199],"4.3%":[200],"sparsity":[203],"structured":[208],"23%":[211],"moderate":[213],"levels":[215],"one-half":[217],"using":[218],"unstructured":[220],"Wanda.":[221],"The":[222,244],"findings":[223],"demonstrate":[224],"our":[226],"approach":[227],"yields":[228],"lightweight":[229],"deployed":[232],"efficiently":[233],"address":[235],"scalability":[237],"challenges":[238],"modern":[240],"systems.":[243],"outcome":[245],"study":[248],"supports":[249],"development":[251],"personalized":[253],"systems":[255],"potential":[257],"applications":[258],"communication":[260],"aids":[261],"individuals":[263],"disorders.":[266]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-12T00:00:00"}