{"id":"https://openalex.org/W4406462045","doi":"https://doi.org/10.1109/slt61566.2024.10832179","title":"Enhancing Speaker Extraction Through Rectifying Target Confusion","display_name":"Enhancing Speaker Extraction Through Rectifying Target Confusion","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462045","doi":"https://doi.org/10.1109/slt61566.2024.10832179"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101614933","display_name":"Jiahe Wang","orcid":"https://orcid.org/0000-0002-7224-9716"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahe Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367662","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-9107-5563"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643115","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-2536-6426"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/confusion","display_name":"Confusion","score":0.7892163991928101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5919561386108398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49069297313690186},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.47508636116981506},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43598639965057373},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07065925002098083},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06904098391532898},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06525960564613342}],"concepts":[{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.7892163991928101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5919561386108398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49069297313690186},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.47508636116981506},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43598639965057373},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07065925002098083},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06904098391532898},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06525960564613342},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2080219784","https://openalex.org/W2333091651","https://openalex.org/W2951130829","https://openalex.org/W2962866211","https://openalex.org/W2972541922","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3027008958","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3113290170","https://openalex.org/W3124666641","https://openalex.org/W3162534564","https://openalex.org/W3206531472","https://openalex.org/W4226021932","https://openalex.org/W4226115251","https://openalex.org/W4288091954","https://openalex.org/W4296070363","https://openalex.org/W4311643440","https://openalex.org/W4367597591","https://openalex.org/W4372260086","https://openalex.org/W4372262790","https://openalex.org/W4372271325","https://openalex.org/W4372340947","https://openalex.org/W4372348071","https://openalex.org/W4375928773","https://openalex.org/W4385822305","https://openalex.org/W4385822391","https://openalex.org/W4385822827","https://openalex.org/W4385822829","https://openalex.org/W4385823017","https://openalex.org/W4392902910","https://openalex.org/W4392902992","https://openalex.org/W4392903066","https://openalex.org/W4396820914","https://openalex.org/W4402112342","https://openalex.org/W6769178842","https://openalex.org/W6777776875","https://openalex.org/W6789284391","https://openalex.org/W6810827206","https://openalex.org/W6847757094","https://openalex.org/W6866852518"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Target":[0,24,70],"Speaker":[1],"Extraction":[2],"(TSE)":[3],"aims":[4],"to":[5,41,75,96],"extract":[6],"target":[7,17,38,58],"speech":[8,34,59],"from":[9],"mixed":[10],"audio":[11],"using":[12],"clues":[13],"that":[14,56,106,132,139],"identify":[15],"the":[16,23,29,32,37,64,77,82,86,89,98,101,108,119],"speaker.":[18,103],"However,":[19],"TSE":[20,83],"often":[21],"faces":[22],"Confusion":[25,71],"(TC)":[26],"problem,":[27],"where":[28],"model":[30,52,84,99],"extracts":[31,100],"interfering":[33],"instead":[35],"of":[36,111,124],"speech,":[39],"leading":[40],"significant":[42],"performance":[43,121],"degradation.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,67],"propose":[49,68],"a":[50,69,93],"novel":[51],"with":[53,131],"two":[54],"branches":[55],"enhance":[57],"extraction":[60],"by":[61],"explicitly":[62],"modeling":[63],"interference.":[65],"Additionally,":[66],"Rectification":[72],"(TCR)":[73],"method":[74,91,116],"address":[76],"aforementioned":[78],"TC":[79],"problem.":[80],"When":[81],"outputs":[85],"wrong":[87],"speaker,":[88],"TCR":[90],"performs":[92],"rectifying":[94],"step":[95],"ensure":[97],"correct":[102],"Experiments":[104],"show":[105],"under":[107,133,140],"train-100":[109],"subset":[110,135],"Libri2Mix":[112],"dataset,":[113],"our":[114],"proposed":[115],"significantly":[117],"improves":[118],"extracting":[120,129],"in":[122],"terms":[123],"SI-SNRi,":[125],"PESQ":[126],"score":[127],"and":[128],"accuracy,":[130],"\u2018mix_clean\u2019":[134],"slightly":[136],"better":[137],"than":[138],"\u2018mix_both\u2019":[141],"subset.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}