{"id":"https://openalex.org/W7163739650","doi":"https://doi.org/10.1016/j.specom.2026.103427","title":"Elevating robust multi-talker ASR by decoupling speaker separation and speech recognition","display_name":"Elevating robust multi-talker ASR by decoupling speaker separation and speech recognition","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7163739650","doi":"https://doi.org/10.1016/j.specom.2026.103427"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2026.103427","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103427","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","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.specom.2026.103427","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138043777","display_name":"Yufeng Yang","orcid":"https://orcid.org/0000-0001-5921-6541"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yufeng Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, OH, United States"],"raw_orcid":"https://orcid.org/0000-0001-5921-6541","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, OH, United States","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan Taherian","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, OH, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, OH, United States","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009379093","display_name":"Vahid Ahmadi Kalkhorani","orcid":"https://orcid.org/0000-0002-4166-1935"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Ahmadi Kalkhorani","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, OH, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, OH, United States","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045649331","display_name":"D F Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5138043777"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":{"value":2870,"currency":"USD","value_usd":2870},"apc_paid":{"value":2870,"currency":"USD","value_usd":2870},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7256917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"182","issue":null,"first_page":"103427","last_page":"103427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7806000113487244,"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":0.7806000113487244,"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":0.19529999792575836,"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":0.004100000020116568,"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/decoupling","display_name":"Decoupling (probability)","score":0.5638999938964844},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4959000051021576},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.438400000333786},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4348999857902527},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8217999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198999762535095},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4169999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4077000021934509},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2994000017642975}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.specom.2026.103427","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103427","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.specom.2026.103427","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103427","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7787890434265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307381","display_name":"National Sleep Foundation","ror":"https://ror.org/00zc1hf95"},{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2024490156","https://openalex.org/W2101045344","https://openalex.org/W2125838338","https://openalex.org/W2141998673","https://openalex.org/W2160815625","https://openalex.org/W2291877678","https://openalex.org/W2559260703","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2963843276","https://openalex.org/W2964058413","https://openalex.org/W2972436155","https://openalex.org/W2972541922","https://openalex.org/W3013139777","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3015834770","https://openalex.org/W3016094953","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3032514799","https://openalex.org/W3094831814","https://openalex.org/W3097777922","https://openalex.org/W3109079702","https://openalex.org/W3109196171","https://openalex.org/W3161590371","https://openalex.org/W3165776651","https://openalex.org/W3171278394","https://openalex.org/W3182358018","https://openalex.org/W3195155284","https://openalex.org/W3198522318","https://openalex.org/W3204618061","https://openalex.org/W3209984917","https://openalex.org/W4223507627","https://openalex.org/W4226390724","https://openalex.org/W4283022709","https://openalex.org/W4294891356","https://openalex.org/W4319862214","https://openalex.org/W4385756463","https://openalex.org/W4385822775","https://openalex.org/W4385823058","https://openalex.org/W4386763469","https://openalex.org/W4388017359","https://openalex.org/W4390660238","https://openalex.org/W4391021760","https://openalex.org/W4391621214","https://openalex.org/W4392908986","https://openalex.org/W4395471098","https://openalex.org/W4400903566","https://openalex.org/W4402116002","https://openalex.org/W4404102497","https://openalex.org/W4406461489","https://openalex.org/W4406461869","https://openalex.org/W4408352769","https://openalex.org/W4410529749","https://openalex.org/W4413359486","https://openalex.org/W4414448470","https://openalex.org/W4415432777","https://openalex.org/W4415433160"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,10,42,57,73,76,81,86,90,107,123,138,168,172,179],"tremendous":[2],"success":[3],"of":[4,12,75,141,182],"automatic":[5],"speech":[6,61,95],"recognition":[7,152],"(ASR)":[8],"with":[9,89,122],"introduction":[11],"deep":[13],"learning,":[14],"its":[15],"performance":[16],"is":[17,119,153,175],"still":[18],"unsatisfactory":[19],"in":[20,28],"many":[21],"real-world":[22],"multi-talker":[23,114,160],"scenarios.":[24],"Speaker":[25],"separation":[26,78,150],"excels":[27],"separating":[29],"individual":[30],"talkers":[31],"but,":[32],"as":[33],"a":[34,50],"frontend,":[35],"it":[36],"introduces":[37],"processing":[38,64],"artifacts":[39],"that":[40,147],"degrade":[41],"ASR":[43,54,82,115,161],"backend":[44,58,91],"trained":[45,92],"on":[46,59,93,106,127,133,184],"clean":[47,94],"speech.":[48,186],"As":[49],"result,":[51],"mainstream":[52,180],"robust":[53,159],"systems":[55],"train":[56],"noisy":[60,185],"to":[62,71,157,177],"mitigate":[63],"artifacts.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,136,164],"propose":[70],"decouple":[72],"training":[74,183],"speaker":[77,149],"frontend":[79],"and":[80,84,129,151],"backend,":[83],"evaluate":[85],"proposed":[87],"system":[88,99],"only.":[96],"Our":[97],"decoupled":[98,173],"achieves":[100],"5.1%":[101],"word":[102],"error":[103],"rates":[104],"(WER)":[105],"Libri2Mix":[108],"dev/test":[109],"sets,":[110],"significantly":[111],"outperforming":[112],"other":[113],"baselines.":[116],"Its":[117],"effectiveness":[118],"also":[120],"demonstrated":[121],"state-of-the-art":[124,144],"7.60%/5.74%":[125],"WERs":[126],"1-ch":[128],"6-ch":[130],"SMS-WSJ.":[131],"Furthermore,":[132],"recorded":[134],"LibriCSS,":[135],"achieve":[137],"speaker-attributed":[139],"WER":[140],"2.92%.":[142],"These":[143],"results":[145],"suggest":[146],"decoupling":[148],"an":[154],"effective":[155],"approach":[156,174,181],"elevate":[158],"performance.":[162],"Finally,":[163],"provide":[165],"insights":[166],"into":[167],"acoustic":[169],"conditions":[170],"where":[171],"expected":[176],"outperform":[178]},"counts_by_year":[],"updated_date":"2026-06-09T06:18:44.609144","created_date":"2026-06-07T00:00:00"}