{"id":"https://openalex.org/W2107807822","doi":"https://doi.org/10.1109/icassp.2009.4960528","title":"Online speaker clustering using incremental learning of an ergodic hidden Markov model","display_name":"Online speaker clustering using incremental learning of an ergodic hidden Markov model","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2107807822","doi":"https://doi.org/10.1109/icassp.2009.4960528","mag":"2107807822"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960528","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/A5031109112","display_name":"Takafumi Koshinaka","orcid":"https://orcid.org/0000-0002-2343-5125"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takafumi Koshinaka","raw_affiliation_strings":["Common Platform Software Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","Common Platform Software Res. Labs., NEC Corporation, Kawasaki, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Common Platform Software Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Common Platform Software Res. Labs., NEC Corporation, Kawasaki, Japan#TAB#","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052317633","display_name":"Kentaro Nagatomo","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Nagatomo","raw_affiliation_strings":["Common Platform Software Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","Common Platform Software Res. Labs., NEC Corporation, Kawasaki, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Common Platform Software Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Common Platform Software Res. Labs., NEC Corporation, Kawasaki, Japan#TAB#","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031109112"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":2.1809,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8928334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"4093","last_page":"4096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9972000122070312,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9972000122070312,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7430301904678345},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7389639019966125},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6700055003166199},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6427176594734192},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.5963881611824036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5460373163223267},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47247809171676636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.464758038520813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4407656788825989},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.43885868787765503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36208564043045044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17429658770561218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430301904678345},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7389639019966125},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6700055003166199},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6427176594734192},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.5963881611824036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5460373163223267},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47247809171676636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.464758038520813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4407656788825989},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.43885868787765503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36208564043045044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17429658770561218},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960528","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":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W194209125","https://openalex.org/W1547083988","https://openalex.org/W1591300715","https://openalex.org/W1618600317","https://openalex.org/W2041273609","https://openalex.org/W2107028904","https://openalex.org/W2159598197","https://openalex.org/W2164031777","https://openalex.org/W2567948266","https://openalex.org/W6607901684","https://openalex.org/W6632910081","https://openalex.org/W6635532411","https://openalex.org/W6636504819","https://openalex.org/W6684028345"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W50969306","https://openalex.org/W2390585021","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W412641959","https://openalex.org/W2944572343","https://openalex.org/W2140773153"],"abstract_inverted_index":{"A":[0],"novel":[1],"online":[2,60],"speaker":[3],"clustering":[4],"method":[5,70,78],"suitable":[6],"for":[7,33],"real-time":[8],"applications":[9],"is":[10],"proposed.":[11],"Using":[12],"an":[13],"ergodic":[14],"hidden":[15],"Markov":[16],"model,":[17],"it":[18],"employs":[19],"incremental":[20],"learning":[21],"based":[22],"on":[23,63],"a":[24,76],"variational":[25],"Bayesian":[26],"framework":[27],"and":[28,52],"provides":[29],"probabilistic":[30],"(non-deterministic)":[31],"decisions":[32],"each":[34],"input":[35],"utterance,":[36],"directly":[37],"considering":[38],"the":[39,68],"specific":[40],"history":[41],"of":[42,55],"preceding":[43],"utterances.":[44],"It":[45],"makes":[46],"possible":[47],"more":[48],"robust":[49],"cluster":[50],"estimation":[51],"precise":[53],"classification":[54],"utterances":[56],"than":[57,75],"do":[58],"conventional":[59,77],"methods.":[61],"Experiments":[62],"meeting-speech":[64],"data":[65],"show":[66],"that":[67],"proposed":[69],"produces":[71],"70-80%":[72],"fewer":[73],"errors":[74],"does.":[79]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}