{"id":"https://openalex.org/W7148862812","doi":"https://doi.org/10.1016/j.ipm.2026.104774","title":"Emotion and noise-robust speaker identification via filter-free self-supervised learning","display_name":"Emotion and noise-robust speaker identification via filter-free self-supervised learning","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7148862812","doi":"https://doi.org/10.1016/j.ipm.2026.104774"},"language":"en","primary_location":{"id":"doi:10.1016/j.ipm.2026.104774","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104774","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.ipm.2026.104774","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025229780","display_name":"Shibani Hamsa","orcid":"https://orcid.org/0000-0002-9422-7251"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Shibani Hamsa","raw_affiliation_strings":["Center for Cyber-Physical Systems, Dept. of Electrical and Computer Engineering, Khalifa University, Abu Dhabi, UAE","Dept. of Medical Sciences and Health Engineering Innovation Group, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-9422-7251","affiliations":[{"raw_affiliation_string":"Center for Cyber-Physical Systems, Dept. of Electrical and Computer Engineering, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]},{"raw_affiliation_string":"Dept. of Medical Sciences and Health Engineering Innovation Group, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042388284","display_name":"Youssef Iraqi","orcid":"https://orcid.org/0000-0003-0112-2600"},"institutions":[{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Youssef Iraqi","raw_affiliation_strings":["School of Computer Science, Mohammed VI Polytechnic University, Morocco"],"raw_orcid":"https://orcid.org/0000-0003-0112-2600","affiliations":[{"raw_affiliation_string":"School of Computer Science, Mohammed VI Polytechnic University, Morocco","institution_ids":["https://openalex.org/I4210131560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068111858","display_name":"Ismail Shahin","orcid":"https://orcid.org/0000-0001-7856-9342"},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ismail Shahin","raw_affiliation_strings":["Dept. of Electrical Engineering, University of Sharjah, Sharjah, UAE"],"raw_orcid":"https://orcid.org/0000-0001-7856-9342","affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, University of Sharjah, Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132857742","display_name":"Ernesto Damiani","orcid":null},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ernesto Damiani","raw_affiliation_strings":["Center for Cyber-Physical Systems, Dept. of Electrical and Computer Engineering, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-9557-6496","affiliations":[{"raw_affiliation_string":"Center for Cyber-Physical Systems, Dept. of Electrical and Computer Engineering, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122321119","display_name":"Kinda Khalaf","orcid":null},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Kinda Khalaf","raw_affiliation_strings":["Dept. of Biomedical Engineering and Biotechnology and Health Engineering Innovation Group, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-3878-2621","affiliations":[{"raw_affiliation_string":"Dept. of Biomedical Engineering and Biotechnology and Health Engineering Innovation Group, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132911530","display_name":"Herbert F. Jelinek","orcid":null},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Herbert F. Jelinek","raw_affiliation_strings":["Dept. of Medical Sciences and Health Engineering Innovation Group, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-1573-3659","affiliations":[{"raw_affiliation_string":"Dept. of Medical Sciences and Health Engineering Innovation Group, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128000618","display_name":"N. Werghi","orcid":null},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Naoufel Werghi","raw_affiliation_strings":["Center for Cyber-Physical Systems, Dept. of Electrical and Computer Engineering, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-5542-448X","affiliations":[{"raw_affiliation_string":"Center for Cyber-Physical Systems, Dept. of Electrical and Computer Engineering, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025229780"],"corresponding_institution_ids":["https://openalex.org/I176601375"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":{"value":3220,"currency":"USD","value_usd":3220},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34703557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":"7","first_page":"104774","last_page":"104774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6890000104904175,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6890000104904175,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.17589999735355377,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.07010000199079514,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5396999716758728},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48080000281333923},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3935000002384186},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37299999594688416},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.36500000953674316},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.3598000109195709},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35249999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022000193595886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5845999717712402},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48080000281333923},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.3050000071525574},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.ipm.2026.104774","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104774","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.ipm.2026.104774","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104774","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322334","display_name":"Khalifa University of Science, Technology and Research","ror":"https://ror.org/05hffr360"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2793701680","https://openalex.org/W2803193013","https://openalex.org/W2895062073","https://openalex.org/W2917572534","https://openalex.org/W3030561575","https://openalex.org/W3082419836","https://openalex.org/W3128793294","https://openalex.org/W3168997536","https://openalex.org/W3196974791","https://openalex.org/W3200874137","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206441910","https://openalex.org/W4206711979","https://openalex.org/W4313204168","https://openalex.org/W4328107267","https://openalex.org/W4386491989","https://openalex.org/W4388230751","https://openalex.org/W4391096300","https://openalex.org/W4402301096","https://openalex.org/W4403117205","https://openalex.org/W4404576841","https://openalex.org/W4404738650","https://openalex.org/W4405265741","https://openalex.org/W4406322111","https://openalex.org/W4407558914","https://openalex.org/W4408326372","https://openalex.org/W4409307724","https://openalex.org/W4409346401"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,20,48],"The":[1],"proposed":[2],"SWF":[3,144,192],"tokenization":[4,112,222],"method,":[5],"dynamically":[6],"capturing":[7],"emotional":[8,73],"subtleties,":[9],"noise":[10],"robustness,":[11],"and":[12,60,72,148,163,182,200,213],"contextual":[13],"information":[14],"to":[15,80,128],"robustly":[16],"preserve":[17,129],"speaker":[18],"identity.":[19],"A":[21],"transformative":[22],"deep-self-supervised":[23],"spectrogram":[24],"transformer":[25],"back-end,":[26],"outperforming":[27,208],"conventional":[28],"approaches":[29],"by":[30],"effectively":[31],"addressing":[32],"their":[33],"inherent":[34],"limitations":[35],"in":[36,70,197,203,221],"preserving":[37],"local":[38,130],"features":[39],"without":[40],"the":[41,81,89,122,143,156,173,191],"need":[42],"for":[43,65,229],"extensive":[44],"labeled":[45],"training":[46],"data.":[47],"Complete":[49],"elimination":[50],"of":[51,83,125,160,168],"dependency":[52],"on":[53,103],"additional":[54],"speech":[55,161,231],"enhancement,":[56],"enabling":[57],"seamless,":[58],"efficient,":[59],"robust":[61,230],"end-to-end":[62],"learning":[63,98],"tailored":[64],"real-world":[66],"deployments.":[67],"Identifying":[68],"speakers":[69],"noisy":[71],"conditions":[74,199],"remains":[75],"a":[76,95,110,117,126,152,166],"significant":[77,188],"challenge":[78],"due":[79],"distortion":[82],"spectral":[84],"cues.":[85],"This":[86],"study":[87],"proposes":[88],"Speech":[90],"Without":[91],"Filter":[92],"(SWF)":[93],"framework,":[94],"novel":[96],"self-supervised":[97],"paradigm":[99,159],"that":[100,114,137,218],"operates":[101],"directly":[102],"raw":[104],"spectrograms.":[105],"Theoretically,":[106],"this":[107],"research":[108],"introduces":[109],"progressive":[111],"mechanism":[113],"acts":[115],"as":[116,224,226],"structural":[118],"inductive":[119],"bias,":[120],"mimicking":[121],"contracting":[123],"path":[124],"U-Net":[127],"spectro-temporal":[131],"continuity.":[132],"Unlike":[133],"standard":[134],"fixed-patch":[135],"Transformers":[136],"often":[138],"smooth":[139],"over":[140],"speaker-specific":[141],"micro-textures,":[142],"architecture":[145],"integrates":[146],"denoising":[147],"feature":[149],"extraction":[150],"into":[151],"single":[153],"stage,":[154],"challenging":[155],"traditional":[157],"decoupled":[158],"enhancement":[162],"recognition.":[164],"Using":[165],"sample":[167],"1.58":[169],"million":[170],"pre-training":[171,227],"instances,":[172],"model":[174,193],"was":[175],"evaluated":[176],"across":[177],"English":[178],"(RAVDESS),":[179],"Arabic":[180],"(ESD),":[181],"stressful":[183],"(SUSAS)":[184],"datasets.":[185],"Results":[186],"demonstrate":[187],"improvements,":[189],"with":[190],"achieving":[194],"91.01%":[195],"accuracy":[196],"clean":[198],"maintaining":[201],"88.5%":[202],"high-noise":[204],"cocktail":[205],"party":[206],"environments,":[207],"state-of-the-art":[209],"models":[210],"like":[211],"WavLM":[212],"HuBERT.":[214],"These":[215],"findings":[216],"suggest":[217],"architectural":[219],"innovation":[220],"is":[223],"critical":[225],"scale":[228],"processing.":[232]},"counts_by_year":[],"updated_date":"2026-04-04T06:15:33.020886","created_date":"2026-04-04T00:00:00"}
