{"id":"https://openalex.org/W2053089284","doi":"https://doi.org/10.1016/j.specom.2012.11.001","title":"Singing speaker clustering based on subspace learning in the GMM mean supervector space","display_name":"Singing speaker clustering based on subspace learning in the GMM mean supervector space","publication_year":2013,"publication_date":"2013-02-11","ids":{"openalex":"https://openalex.org/W2053089284","doi":"https://doi.org/10.1016/j.specom.2012.11.001","mag":"2053089284"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2012.11.001","doi":"https://doi.org/10.1016/j.specom.2012.11.001","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2012.11.001","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0167639312001306/pdf","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.sciencedirect.com/science/article/pii/S0167639312001306/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060747272","display_name":"Mahnoosh Mehrabani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahnoosh Mehrabani","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057910370"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2900,"currency":"USD","value_usd":2900},"apc_paid":{"value":2900,"currency":"USD","value_usd":2900},"fwci":2.2121,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88509089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"55","issue":"5","first_page":"653","last_page":"666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9541000127792358,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9541000127792358,"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/T10860","display_name":"Speech and Audio Processing","score":0.03229999914765358,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0024999999441206455,"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/subspace-learning","display_name":"subspace learning","score":0.7720000147819519},{"id":"https://openalex.org/keywords/plda","display_name":"PLDA","score":0.4189999997615814},{"id":"https://openalex.org/keywords/lpp","display_name":"LPP","score":0.6510000228881836},{"id":"https://openalex.org/keywords/two-stage-clustering","display_name":"two-stage clustering","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612758278846741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7545535564422607},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6952378153800964},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5531835556030273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299694538116455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5204306244850159},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5169941186904907},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5032572150230408},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4964640736579895},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4862788915634155},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.specom.2012.11.001","doi":"https://doi.org/10.1016/j.specom.2012.11.001","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2012.11.001","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0167639312001306/pdf","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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.2012.11.001","doi":"https://doi.org/10.1016/j.specom.2012.11.001","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2012.11.001","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0167639312001306/pdf","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2053089284.pdf","grobid_xml":"https://content.openalex.org/works/W2053089284.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W40959531","https://openalex.org/W177407077","https://openalex.org/W189651667","https://openalex.org/W1502693945","https://openalex.org/W1554663460","https://openalex.org/W1589137271","https://openalex.org/W1625928172","https://openalex.org/W1964208564","https://openalex.org/W1990368529","https://openalex.org/W2016381774","https://openalex.org/W2036365100","https://openalex.org/W2041823554","https://openalex.org/W2069883713","https://openalex.org/W2072328708","https://openalex.org/W2090861223","https://openalex.org/W2097590279","https://openalex.org/W2099904336","https://openalex.org/W2110530876","https://openalex.org/W2113076747","https://openalex.org/W2117553576","https://openalex.org/W2121812409","https://openalex.org/W2121892718","https://openalex.org/W2127914268","https://openalex.org/W2136439176","https://openalex.org/W2141262306","https://openalex.org/W2144130981","https://openalex.org/W2147147599","https://openalex.org/W2147157320","https://openalex.org/W2148374980","https://openalex.org/W2150260301","https://openalex.org/W2150574373","https://openalex.org/W2154872931","https://openalex.org/W2155517073","https://openalex.org/W2156718197","https://openalex.org/W2159591770","https://openalex.org/W2161939451","https://openalex.org/W2165108269","https://openalex.org/W2398758317","https://openalex.org/W2406597575","https://openalex.org/W3031363333","https://openalex.org/W4256128890","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2406597575","https://openalex.org/W2148374980","https://openalex.org/W2114023597","https://openalex.org/W2147157320","https://openalex.org/W2747754462","https://openalex.org/W2162767715","https://openalex.org/W2566391936","https://openalex.org/W2161939451","https://openalex.org/W2044517686","https://openalex.org/W2150260301"],"abstract_inverted_index":{"In":[0],"this":[1,47],"study,":[2],"we":[3],"propose":[4],"algorithms":[5],"based":[6,103,129,134,141,208],"on":[7,104,130,135,142],"subspace":[8,123,168],"learning":[9,124],"in":[10,36,68,165,170],"the":[11,37],"GMM":[12],"mean":[13],"supervector":[14],"space":[15,85],"to":[16,50,65,111,180,224],"improve":[17,63,225],"performance":[18],"of":[19,40,46,83,87,91,95,122,202],"speaker":[20,118,173,232],"clustering":[21,72,115,139,190,209],"with":[22],"speech":[23,54,58,69,229],"from":[24],"both":[25],"reading":[26,92,203],"and":[27,60,77,93,132,159,204,206,236],"singing.":[28],"As":[29],"a":[30,41,88,101,145,166,171,196,200,216],"speaking":[31,181],"style,":[32],"singing":[33,94],"introduces":[34],"changes":[35],"time-frequency":[38],"structure":[39],"speaker\u2019s":[42],"voice.":[43],"The":[44,219],"purpose":[45],"study":[48],"is":[49,109,144,163,177,184],"introduce":[51],"advancements":[52,220],"for":[53,81,97,199,228],"systems":[55],"such":[56,74],"as":[57,75],"indexing":[59],"retrieval":[61],"which":[62],"robustness":[64],"intrinsic":[66],"variations":[67],"production.":[70],"Speaker":[71],"techniques":[73,223],"k-means":[76,217],"hierarchical":[78,197],"are":[79,126,153],"explored":[80],"analysis":[82],"acoustic":[84],"differences":[86],"corpus":[89],"consisting":[90],"lyrics":[96],"each":[98,161],"speaker.":[99],"Furthermore,":[100],"distance":[102],"fuzzy":[105],"c-means":[106],"membership":[107],"degrees":[108],"proposed":[110,138],"more":[112,172],"accurately":[113],"measure":[114],"difficulty":[116],"or":[117],"confusability.":[119],"Two":[120],"categories":[121],"methods":[125],"studied:":[127],"unsupervised":[128],"LPP,":[131],"supervised":[133],"PLDA.":[136],"Our":[137],"method":[140],"PLDA":[143,167,207],"two":[146],"stage":[147],"algorithm:":[148],"where":[149],"first,":[150],"initial":[151],"clusters":[152],"obtained":[154],"using":[155],"full":[156],"dimension":[157],"supervectors,":[158],"next,":[160],"cluster":[162],"refined":[164],"resulting":[169],"dependent":[174],"representation":[175],"that":[176,186],"less":[178],"sensitive":[179],"style.":[182],"It":[183],"shown":[185],"LPP":[187],"improves":[188],"average":[189],"accuracy":[191,211],"by":[192,212],"5.1%":[193],"absolute":[194,214],"versus":[195,215],"baseline":[198],"mixture":[201],"singing,":[205],"increases":[210],"9.6%":[213],"baseline.":[218],"offer":[221],"novel":[222],"model":[226],"formulation":[227],"applications":[230],"including":[231],"ID,":[233],"audio":[234,237],"search,":[235],"content":[238],"analysis.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
