{"id":"https://openalex.org/W2889940807","doi":"https://doi.org/10.1109/icassp.2018.8462104","title":"Maximum-Likelihood Online Speaker Diarization in Noisy Meetings Based on Categorical Mixture Model and Probabilistic Spatial Dictionary","display_name":"Maximum-Likelihood Online Speaker Diarization in Noisy Meetings Based on Categorical Mixture Model and Probabilistic Spatial Dictionary","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2889940807","doi":"https://doi.org/10.1109/icassp.2018.8462104","mag":"2889940807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5101438174","display_name":"Nobutaka Ito","orcid":"https://orcid.org/0000-0001-9740-6848"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ito","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070595658","display_name":"Takashi Makino","orcid":"https://orcid.org/0000-0003-4600-9353"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Makino","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"546","last_page":"550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9980999827384949,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.88965904712677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7203139066696167},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5543258190155029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5411722660064697},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5243744850158691},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5077891945838928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45985230803489685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39147502183914185},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19426360726356506},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.19338497519493103}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.88965904712677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203139066696167},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5543258190155029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5411722660064697},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5243744850158691},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5077891945838928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45985230803489685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39147502183914185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19426360726356506},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.19338497519493103},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1557470594","https://openalex.org/W1612003148","https://openalex.org/W1902027874","https://openalex.org/W1991082011","https://openalex.org/W2005733316","https://openalex.org/W2043216213","https://openalex.org/W2081074144","https://openalex.org/W2164031777","https://openalex.org/W2536165811","https://openalex.org/W2714509385","https://openalex.org/W2767042273","https://openalex.org/W6636440780","https://openalex.org/W6651792828","https://openalex.org/W6661582794","https://openalex.org/W6684028345","https://openalex.org/W6728819206","https://openalex.org/W6745736146"],"related_works":["https://openalex.org/W2028211458","https://openalex.org/W2144208207","https://openalex.org/W1521049138","https://openalex.org/W2111874347","https://openalex.org/W1509309911","https://openalex.org/W2128773298","https://openalex.org/W1497807607","https://openalex.org/W2041797852","https://openalex.org/W3120512183","https://openalex.org/W2118860825"],"abstract_inverted_index":{"In":[0,54,92],"this":[1,48,55],"paper,":[2],"we":[3,38],"propose":[4],"a":[5,12,114,135,146],"maximum-likelihood":[6,81,107],"online":[7],"diarization":[8,44,69,84,101,125,147],"method":[9,45,96,144],"based":[10,63,88],"on":[11,64,89,134],"probabilistic":[13],"spatial":[14,25,51],"dictionary.":[15],"This":[16,109],"dictionary":[17,49],"consists":[18],"of":[19,24,31,34],"the":[20,65,73,80,83,94,106,142,155],"given":[21],"probability":[22],"distribution":[23],"features":[26],"for":[27],"each":[28],"possible":[29],"direction":[30],"arrival":[32],"(DOA)":[33],"source":[35],"signals.":[36],"Recently,":[37],"have":[39],"developed":[40],"an":[41,132],"online,":[42],"noise-robust":[43],"by":[46,112,150],"utilizing":[47],"as":[50,127],"prior":[52],"information.":[53],"method,":[56],"DOA":[57,74,98,122],"estimation":[58,75,99],"is":[59,70,76,85,110],"first":[60],"performed":[61,77,86],"frame-wise":[62],"dictionary,":[66],"and":[67,100,103,124,139],"subsequently":[68],"performed.":[71],"Although":[72],"optimally":[78,104],"in":[79,105],"sense,":[82],"suboptimally":[87],"some":[90],"heuristics.":[91],"contrast,":[93],"proposed":[95,143],"performs":[97],"jointly":[102],"sense.":[108],"realized":[111],"introducing":[113],"categorical":[115],"mixture":[116],"model":[117],"(CMM),":[118],"which":[119],"has":[120],"source-wise":[121],"information":[123,126],"unknown":[128],"parameters.":[129],"We":[130],"conducted":[131],"experiment":[133],"real-world":[136],"meeting":[137],"dataset,":[138],"confirmed":[140],"that":[141],"reduced":[145],"error":[148],"rate":[149],"absolute":[151],"2.7%":[152],"compared":[153],"to":[154],"above":[156],"conventional":[157],"method.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}