{"id":"https://openalex.org/W3116025434","doi":"https://doi.org/10.1109/taslp.2020.3045556","title":"Speaker Separation Using Speaker Inventories and Estimated Speech","display_name":"Speaker Separation Using Speaker Inventories and Estimated Speech","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3116025434","doi":"https://doi.org/10.1109/taslp.2020.3045556","mag":"3116025434"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3045556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3045556","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"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":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062250845"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.5153,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83726136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"537","last_page":"546"},"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":0.9995999932289124,"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":0.9991999864578247,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7521429061889648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7226470708847046},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7203577160835266},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6859759092330933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6764466762542725},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08587914705276489}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7521429061889648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7226470708847046},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7203577160835266},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6859759092330933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6764466762542725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08587914705276489}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3045556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3045556","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2075606107","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2550397165","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2749510669","https://openalex.org/W2786625961","https://openalex.org/W2799930831","https://openalex.org/W2800022361","https://openalex.org/W2801798988","https://openalex.org/W2803322398","https://openalex.org/W2804644188","https://openalex.org/W2890820256","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2910254446","https://openalex.org/W2924115626","https://openalex.org/W2936302822","https://openalex.org/W2938600350","https://openalex.org/W2938646939","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962865004","https://openalex.org/W2964238697","https://openalex.org/W2972460025","https://openalex.org/W2973062255","https://openalex.org/W2996969697","https://openalex.org/W3000358149","https://openalex.org/W3008400075","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W4289665794","https://openalex.org/W6631362777","https://openalex.org/W6759323020","https://openalex.org/W6762182681"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"We":[0,85],"propose":[1],"speaker":[2,5,14,20,26,29,33,41,47,76,91],"separation":[3,27,34,42,77,92],"using":[4,28,35,79],"inventories":[6,30],"and":[7,16,32,58,93],"estimated":[8,17,36],"speech":[9,18,37,59,94],"(SSUSIES),":[10],"a":[11,68],"framework":[12],"leveraging":[13],"profiles":[15],"for":[19],"separation.":[21,84],"SSUSIES":[22],"contains":[23],"two":[24],"methods,":[25],"(SSUSI)":[31],"(SSUES).":[38],"SSUSI":[39,61],"performs":[40],"with":[43],"the":[44,51,80,87],"help":[45],"of":[46,53,82],"inventory.":[48],"By":[49],"combining":[50],"advantages":[52],"permutation":[54],"invariant":[55],"training":[56],"(PIT)":[57],"extraction,":[60],"significantly":[62],"outperforms":[63],"conventional":[64],"approaches.":[65],"SSUES":[66],"is":[67],"widely":[69],"applicable":[70],"technique":[71],"that":[72],"can":[73],"substantially":[74],"improve":[75],"performance":[78],"output":[81],"first-pass":[83],"evaluate":[86],"models":[88],"on":[89],"both":[90],"recognition":[95],"metrics.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}