{"id":"https://openalex.org/W1991356269","doi":"https://doi.org/10.1109/tasl.2012.2204050","title":"Statistical Utterance Comparison for Speaker Clustering Using Factor Analysis","display_name":"Statistical Utterance Comparison for Speaker Clustering Using Factor Analysis","publication_year":2012,"publication_date":"2012-06-08","ids":{"openalex":"https://openalex.org/W1991356269","doi":"https://doi.org/10.1109/tasl.2012.2204050","mag":"1991356269"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2204050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2204050","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 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/A5055671046","display_name":"Woojay Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woojay Jeon","raw_affiliation_strings":["Samsung Electronics Limited, Suwon, South Korea","Samsung Electron., Suwon, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Limited, Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Electron., Suwon, South Korea#TAB#","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063227156","display_name":"Changxue Ma","orcid":"https://orcid.org/0009-0001-8527-6131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changxue Ma","raw_affiliation_strings":["DTS, Inc., Calabasas, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTS, Inc., Calabasas, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113696646","display_name":"Du\u0161an Macho","orcid":null},"institutions":[{"id":"https://openalex.org/I1333370159","display_name":"Motorola (United States)","ror":"https://ror.org/01hafxd32","country_code":"US","type":"company","lineage":["https://openalex.org/I1333370159"]},{"id":"https://openalex.org/I14637135","display_name":"Motorola (South Korea)","ror":"https://ror.org/00y09zk14","country_code":"KR","type":"company","lineage":["https://openalex.org/I1333370159","https://openalex.org/I14637135"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Dusan Macho","raw_affiliation_strings":["Motorola Solutions, Schaumburg, IL, USA","[Motorola Solutions, Schaumburg, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola Solutions, Schaumburg, IL, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"[Motorola Solutions, Schaumburg, IL, USA]","institution_ids":["https://openalex.org/I14637135"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78537202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","issue":"9","first_page":"2482","last_page":"2491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9947999715805054,"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/T11309","display_name":"Music and Audio Processing","score":0.9922999739646912,"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/similarity","display_name":"Similarity (geometry)","score":0.6881586313247681},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6849764585494995},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6549943089485168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5708519220352173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5387697219848633},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5250047445297241},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48529762029647827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.463906466960907},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45879030227661133},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4529584050178528},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4315645396709442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3309590220451355}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6881586313247681},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6849764585494995},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6549943089485168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5708519220352173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5387697219848633},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5250047445297241},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48529762029647827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.463906466960907},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45879030227661133},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4529584050178528},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4315645396709442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3309590220451355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2012.2204050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2204050","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W45771966","https://openalex.org/W2042606741","https://openalex.org/W2098726438","https://openalex.org/W2103580452","https://openalex.org/W2106810246","https://openalex.org/W2107825049","https://openalex.org/W2110136872","https://openalex.org/W2110530876","https://openalex.org/W2115599677","https://openalex.org/W2125642021","https://openalex.org/W2128484087","https://openalex.org/W2131118559","https://openalex.org/W2136879537","https://openalex.org/W2137319143","https://openalex.org/W2155386343","https://openalex.org/W2159591770","https://openalex.org/W2161939451","https://openalex.org/W2162158162","https://openalex.org/W2162627003","https://openalex.org/W2165108269","https://openalex.org/W2166980079","https://openalex.org/W6601867588"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"We":[0,91,122],"propose":[1],"a":[2,74,116,128],"novel":[3],"method":[4],"of":[5,52,77,119],"measuring":[6],"the":[7,31,34,38,58,85,100,106,124,133,150],"similarity":[8,26,59,148],"between":[9],"two":[10,145],"or":[11],"more":[12],"speech":[13,82],"utterances":[14,35],"for":[15,80],"speaker":[16,129],"clustering,":[17],"based":[18],"on":[19],"probability":[20,32],"theory":[21],"and":[22,41,45,54,64,96,138,154],"factor":[23],"analysis.":[24],"The":[25,66],"function":[27,60,68],"is":[28],"formulated":[29],"as":[30],"that":[33,140],"originated":[36],"from":[37],"same":[39],"speaker,":[40],"uses":[42],"statistical":[43],"eigenvoice":[44],"eigenchannel":[46],"models":[47],"to":[48,61,88,108],"incorporate":[49],"physical":[50],"knowledge":[51],"interspeaker":[53],"intraspeaker":[55],"variabilities,":[56],"allowing":[57,84],"be":[62,70,89,103],"trainable":[63],"robust.":[65],"comparison":[67],"can":[69,102],"efficiently":[71],"computed":[72],"using":[73,93,132],"compact":[75],"set":[76,118],"sufficient":[78,120],"statistics":[79],"each":[81],"utterance,":[83],"acoustic":[86],"features":[87],"discarded.":[90],"begin":[92],"only":[94],"eigenvoices,":[95],"then":[97],"show":[98,139],"how":[99],"eigenchannels":[101],"incorporated":[104],"into":[105],"equation":[107],"result":[109],"in":[110,127],"an":[111],"identical":[112],"form":[113],"but":[114],"with":[115],"different":[117],"statistics.":[121],"test":[123],"proposed":[125],"model":[126],"clustering":[130],"task":[131],"CALLHOME":[134],"telephone":[135],"conversation":[136],"corpus":[137],"it":[141],"performs":[142],"better":[143],"than":[144],"other":[146],"well-known":[147],"measures:":[149],"Cross-Likelihood":[151],"Ratio":[152,157],"(CLR)":[153],"Generalized":[155],"Likelihood":[156],"(GLR).":[158]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
