{"id":"https://openalex.org/W2106810246","doi":"https://doi.org/10.1109/icassp.2011.5947361","title":"An utterance comparison model for speaker clustering using factor analysis","display_name":"An utterance comparison model for speaker clustering using factor analysis","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2106810246","doi":"https://doi.org/10.1109/icassp.2011.5947361","mag":"2106810246"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5055671046","display_name":"Woojay Jeon","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woojay Jeon","raw_affiliation_strings":["Motorola, Inc., Schaumburg, IL, USA","Motorola, Inc., Schaumburg, Illinois, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola, Inc., Schaumburg, IL, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"Motorola, Inc., Schaumburg, Illinois, U.S.A","institution_ids":["https://openalex.org/I1333370159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063227156","display_name":"Changxue Ma","orcid":"https://orcid.org/0009-0001-8527-6131"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changxue Ma","raw_affiliation_strings":["Motorola, Inc., Schaumburg, IL, USA","Motorola, Inc., Schaumburg, Illinois, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola, Inc., Schaumburg, IL, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"Motorola, Inc., Schaumburg, Illinois, U.S.A","institution_ids":["https://openalex.org/I1333370159"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dusan Macho","raw_affiliation_strings":["Motorola, Inc., Schaumburg, IL, USA","Motorola, Inc., Schaumburg, Illinois, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola, Inc., Schaumburg, IL, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"Motorola, Inc., Schaumburg, Illinois, U.S.A","institution_ids":["https://openalex.org/I1333370159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1333370159"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4528","last_page":"4531"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9502999782562256,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/utterance","display_name":"Utterance","score":0.798497200012207},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6385264992713928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6339575052261353},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5710626840591431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5516102910041809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505702018737793},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5012657642364502},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49499958753585815},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.47907692193984985},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4527006149291992},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4373212456703186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3405730128288269},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3286314606666565},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3223249316215515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09526154398918152}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.798497200012207},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6385264992713928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6339575052261353},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5710626840591431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5516102910041809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505702018737793},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5012657642364502},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49499958753585815},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.47907692193984985},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4527006149291992},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4373212456703186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3405730128288269},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3286314606666565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3223249316215515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09526154398918152},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/icassp.2011.5947361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2110530876","https://openalex.org/W2125642021","https://openalex.org/W2128484087","https://openalex.org/W2136879537","https://openalex.org/W2137319143","https://openalex.org/W2159591770","https://openalex.org/W2165108269","https://openalex.org/W6678433015"],"related_works":["https://openalex.org/W3133700904","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W3033557797","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"We":[0,56],"propose":[1],"a":[2,32,61],"novel":[3],"utterance":[4,39],"comparison":[5],"model":[6,28,59],"based":[7],"on":[8,31],"probability":[9],"theory":[10],"and":[11,40,90],"factor":[12],"analysis":[13],"that":[14],"computes":[15],"the":[16,58,84],"likelihood":[17],"of":[18,34,53],"two":[19],"speech":[20,54],"utterances":[21,44],"originating":[22],"from":[23,37],"die":[24,50,68],"same":[25],"speaker.":[26],"The":[27],"depends":[29],"only":[30],"set":[33],"statistics":[35,47],"extracted":[36],"each":[38],"can":[41],"efficiently":[42],"compare":[43],"using":[45],"these":[46],"without":[48],"requiring":[49],"indefinite":[51],"storage":[52],"features.":[55],"apply":[57],"as":[60],"distance":[62],"metric":[63],"for":[64],"speaker":[65],"clustering":[66],"in":[67],"CALLHOME":[69],"telephone":[70],"conversation":[71],"corpus":[72],"to":[73,78],"achieve":[74],"competitive":[75],"results":[76],"compared":[77],"three":[79],"other":[80],"known":[81],"similarity":[82],"measures:":[83],"Generalized":[85],"Likelihood":[86],"Ratio,":[87,89],"Cross-Likelihood":[88],"eigenvoice":[91],"distance.":[92]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}