{"id":"https://openalex.org/W2150260301","doi":"https://doi.org/10.1109/icassp.2009.4960530","title":"Generative model-based speaker clustering via mixture of von Mises-Fisher distributions","display_name":"Generative model-based speaker clustering via mixture of von Mises-Fisher distributions","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2150260301","doi":"https://doi.org/10.1109/icassp.2009.4960530","mag":"2150260301"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113805086","display_name":"Stephen M. Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen M. Chu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas S. Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100662187"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.1809,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89640289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4101","last_page":"4104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9980999827384949,"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":0.9919000267982483,"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/mixture-model","display_name":"Mixture model","score":0.8589109182357788},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.5983995199203491},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5719900131225586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5050399899482727},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4984726905822754},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.47309020161628723},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.4487065076828003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42763012647628784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4222896695137024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39980706572532654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34743809700012207},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19010332226753235},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.1850631833076477},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.13408246636390686}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8589109182357788},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.5983995199203491},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5719900131225586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5050399899482727},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4984726905822754},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.47309020161628723},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.4487065076828003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42763012647628784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4222896695137024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39980706572532654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34743809700012207},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19010332226753235},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.1850631833076477},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.13408246636390686}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W71184241","https://openalex.org/W76945434","https://openalex.org/W1560013842","https://openalex.org/W1663973292","https://openalex.org/W1981081578","https://openalex.org/W2002111936","https://openalex.org/W2041823554","https://openalex.org/W2049633694","https://openalex.org/W2069883713","https://openalex.org/W2090861223","https://openalex.org/W2107617395","https://openalex.org/W2110530876","https://openalex.org/W2129244720","https://openalex.org/W2141262306","https://openalex.org/W2145001205","https://openalex.org/W2147147599","https://openalex.org/W2158353986","https://openalex.org/W2159591770","https://openalex.org/W2161877964","https://openalex.org/W2166980079","https://openalex.org/W2167206253","https://openalex.org/W2338994564","https://openalex.org/W2799061466","https://openalex.org/W4205687621","https://openalex.org/W4212863985","https://openalex.org/W6602844930","https://openalex.org/W6603105437","https://openalex.org/W6659344013","https://openalex.org/W6676027155"],"related_works":["https://openalex.org/W2473373438","https://openalex.org/W2368486525","https://openalex.org/W1783992599","https://openalex.org/W2114899076","https://openalex.org/W2077224612","https://openalex.org/W2153481672","https://openalex.org/W2153238387","https://openalex.org/W4312864369","https://openalex.org/W84255947","https://openalex.org/W2045588782"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,38,50,56,77,119,139],"generative":[4],"model-based":[5],"speaker":[6,132],"clustering":[7,133],"algorithm":[8,23,35],"in":[9,83],"the":[10,31,42,84,89,110,116,126,136],"maximum":[11],"posteriori":[13],"adapted":[14],"Gaussian":[15,142],"mixture":[16,39,78,120,140],"model":[17,40,57,85,128],"(GMM)":[18],"mean":[19,71],"supervector":[20],"space.":[21],"The":[22,65],"can":[24],"be":[25],"viewed":[26],"as":[27,125],"an":[28],"extension":[29],"of":[30,69,79,118,121,138,141],"standard":[32],"expectation":[33],"maximization":[34],"for":[36],"fitting":[37],"to":[41,160],"data,":[43],"which":[44],"iterates":[45],"between":[46],"two":[47],"steps":[48],"-":[49,61],"sample":[51,90],"re-assignment":[52,91],"step":[53,59],"(E-step)":[54],"and":[55,101,163,167],"re-estimation":[58,86],"(M-step)":[60],"until":[62],"it":[63],"converges.":[64],"directional":[66],"scattering":[67],"patterns":[68],"GMM":[70],"supervectors":[72],"suggest":[73],"that":[74,115,148,155,164],"we":[75],"employ":[76],"von":[80,122],"Mises-Fisher":[81,123],"distributions":[82,124],"step.":[87],"In":[88],"step,":[92],"four":[93],"sample-to-mixture":[94],"assignment":[95,151,157],"strategies,":[96],"namely":[97],"soft,":[98],"hard,":[99],"stochastic,":[100],"deterministic":[102,149],"annealing":[103,150],"assignments,":[104],"are":[105],"used.":[106],"Our":[107],"experiments":[108],"on":[109],"GALE":[111],"Mandarin":[112],"dataset":[113],"show":[114],"use":[117,137],"underlying":[127],"yields":[129],"significantly":[130],"higher":[131],"accuracies":[134],"than":[135],"distributions.":[143],"It":[144],"is":[145,158],"further":[146],"shown":[147],"outperforms":[152],"soft":[153,156,166],"assignment,":[154,162],"comparable":[159],"stochastic":[161,168],"both":[165],"assignments":[169],"outperform":[170],"hard":[171],"assignment.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}