{"id":"https://openalex.org/W4285106251","doi":"https://doi.org/10.1109/taslp.2022.3166262","title":"Singer Diarization for Polyphonic Music With Unison Singing","display_name":"Singer Diarization for Polyphonic Music With Unison Singing","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285106251","doi":"https://doi.org/10.1109/taslp.2022.3166262"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3166262","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3166262","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767568.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767568.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008138836","display_name":"Hitoshi Suda","orcid":"https://orcid.org/0000-0003-2648-363X"},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Suda","raw_affiliation_strings":["Department of Engineering, University of Tokyo, Bunkyo-ku, Tokyo, Japan","Department of Electrical Engineering and Information Systems, The University of Tokyo Graduate School of Engineering Faculty of Engineering, 83892 Bunkyo-ku, Japan, 113-8656"],"raw_orcid":"https://orcid.org/0000-0003-2648-363X","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I153327471"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Systems, The University of Tokyo Graduate School of Engineering Faculty of Engineering, 83892 Bunkyo-ku, Japan, 113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["Department of Engineering, University of Tokyo, Bunkyo-ku, Tokyo, Japan","Department of Electrical Engineering and Information Systems, The University of Tokyo, 13143 Bunkyo-ku, Japan, 113-0033"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I153327471"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Systems, The University of Tokyo, 13143 Bunkyo-ku, Japan, 113-0033","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098968","display_name":"Satoru Fukayama","orcid":"https://orcid.org/0000-0001-6506-2796"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Fukayama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan, 305-0051"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan, 305-0051","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu Nakano","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","Human Informatics and Interaction Research Institute, National Institute of Advanced Industrial Science and Technology, 13508 Tsukuba, Ibaraki, Japan, 305-8568"],"raw_orcid":"https://orcid.org/0000-0003-1167-0977","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Human Informatics and Interaction Research Institute, National Institute of Advanced Industrial Science and Technology, 13508 Tsukuba, Ibaraki, Japan, 305-8568","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.707,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66373084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"30","issue":null,"first_page":"1531","last_page":"1545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9284093379974365},{"id":"https://openalex.org/keywords/unison","display_name":"Unison","score":0.8944331407546997},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7444107532501221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7369884848594666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6173003911972046},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5924667119979858},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5721518397331238},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4954577684402466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29918235540390015},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24310243129730225},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2357977032661438},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19216585159301758}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9284093379974365},{"id":"https://openalex.org/C2780304638","wikidata":"https://www.wikidata.org/wiki/Q176224","display_name":"Unison","level":2,"score":0.8944331407546997},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7444107532501221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7369884848594666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173003911972046},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5924667119979858},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5721518397331238},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4954577684402466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29918235540390015},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24310243129730225},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2357977032661438},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19216585159301758},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3166262","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3166262","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767568.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/taslp.2022.3166262","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3166262","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09767568.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285106251.pdf","grobid_xml":"https://content.openalex.org/works/W4285106251.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W24570992","https://openalex.org/W1583001605","https://openalex.org/W1901129140","https://openalex.org/W1904711963","https://openalex.org/W1963838958","https://openalex.org/W1965255698","https://openalex.org/W1965819578","https://openalex.org/W1999454387","https://openalex.org/W2003784299","https://openalex.org/W2007664495","https://openalex.org/W2048497537","https://openalex.org/W2067709094","https://openalex.org/W2081074144","https://openalex.org/W2088234478","https://openalex.org/W2097583714","https://openalex.org/W2101775574","https://openalex.org/W2107058149","https://openalex.org/W2129120544","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2168987487","https://openalex.org/W2344822617","https://openalex.org/W2638067502","https://openalex.org/W2890964092","https://openalex.org/W2902653098","https://openalex.org/W2906098386","https://openalex.org/W2915347754","https://openalex.org/W2962898354","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2972949456","https://openalex.org/W2997419692","https://openalex.org/W3008357631","https://openalex.org/W3020336359","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3037149862","https://openalex.org/W3095212884","https://openalex.org/W3105031100","https://openalex.org/W3159302906","https://openalex.org/W3162347631","https://openalex.org/W3195050710","https://openalex.org/W3198827946","https://openalex.org/W4214556932","https://openalex.org/W6628911050","https://openalex.org/W6704529918","https://openalex.org/W6738708339","https://openalex.org/W6756560125"],"related_works":["https://openalex.org/W2365473327","https://openalex.org/W2796195741","https://openalex.org/W2258736945","https://openalex.org/W1994757015","https://openalex.org/W2016891255","https://openalex.org/W4309134657","https://openalex.org/W4372259973","https://openalex.org/W3001220525","https://openalex.org/W4384929466","https://openalex.org/W4285106251"],"abstract_inverted_index":{"This":[0,105],"paper":[1,106,125],"introduces":[2],"a":[3,11,46,51,109,127,140,158,189],"new":[4,110,190],"framework":[5,112,164,184,213],"for":[6,57,218],"singer":[7,55,173],"diarization,":[8],"which":[9,134,197],"is":[10,48,135,142,185,198],"technique":[12,169],"to":[13,29,85,170],"reveal":[14],"who":[15],"sings":[16],"when":[17],"in":[18,37,65,77,114,121,137,221],"songs":[19],"with":[20,74],"multiple":[21,58,75],"singers.":[22],"Although":[23],"various":[24],"techniques":[25],"have":[26],"been":[27,62,83],"developed":[28],"analyze":[30],"and":[31,54,102],"extract":[32,171],"features":[33],"of":[34,42,68,97,178,193,223],"singing":[35,69,93,101,115,151,159,181,195],"voices":[36,94,152],"musical":[38],"audio":[39],"signals,":[40],"most":[41],"them":[43],"assume":[44],"that":[45,210],"song":[47,141],"sung":[49,143],"by":[50,144,156,187],"single":[52],"singer,":[53],"diarization":[56,81,111,220,224],"singers":[59],"has":[60,82],"not":[61],"well":[63,95],"studied":[64],"the":[66,163,179,211,215],"field":[67],"information":[70],"processing.":[71],"To":[72,117],"deal":[73],"speakers":[76],"speech":[78,88,103],"analysis,":[79],"speaker":[80,219],"explored":[84],"handle":[86,92],"overlapped":[87],"voices,":[89,196],"but":[90],"cannot":[91],"because":[96],"acoustic":[98,129],"differences":[99],"between":[100],"voices.":[104,116,182],"therefore":[107],"proposes":[108,126],"specialized":[113],"achieve":[118],"high":[119],"accuracy":[120],"overlap":[122],"detection,":[123],"this":[124],"novel":[128],"feature":[130],"named":[131],"Cosacorr":[132],"score,":[133],"helpful":[136],"estimating":[138],"whether":[139],"more":[145],"than":[146],"one":[147],"singer.":[148],"After":[149],"extracting":[150],"from":[153,175],"polyphonic":[154],"music":[155],"using":[157,188,200],"voice":[160],"separation":[161],"technique,":[162],"adopts":[165],"an":[166],"existing":[167],"ArcFace":[168],"discriminative":[172],"representations":[174],"short":[176],"segments":[177],"separated":[180],"The":[183,206],"evaluated":[186],"private":[191],"dataset":[192],"unison":[194],"constructed":[199],"commercially":[201],"available":[202],"compact":[203],"discs":[204],"(CDs).":[205],"experimental":[207],"results":[208],"show":[209],"proposed":[212],"outperformed":[214],"baseline":[216],"method":[217],"terms":[222],"error":[225],"rate":[226],"(DER).":[227]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
