{"id":"https://openalex.org/W2057099756","doi":"https://doi.org/10.1109/aspaa.2009.5346517","title":"A probabilistic speaker clustering for DOA-based diarization","display_name":"A probabilistic speaker clustering for DOA-based diarization","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2057099756","doi":"https://doi.org/10.1109/aspaa.2009.5346517","mag":"2057099756"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2009.5346517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2009.5346517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","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/A5000004444","display_name":"Katsuhiko Ishiguro","orcid":null},"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":"Katsuhiko Ishiguro","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan","NTT Communication Science Laboratories, Kyoto, 619-0237 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, 619-0237 Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073170587","display_name":"Takeshi Yamada","orcid":"https://orcid.org/0000-0002-5744-8469"},"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":"Takeshi Yamada","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan","NTT Communication Science Laboratories, Kyoto, 619-0237 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, 619-0237 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, Kyoto, Japan","NTT Communication Science Laboratories, Kyoto, 619-0237 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, 619-0237 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, Kyoto, Japan","NTT Communication Science Laboratories, Kyoto, 619-0237 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, 619-0237 Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.453,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73176223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"241","last_page":"244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9276139736175537},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8066279888153076},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7417469024658203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7379547357559204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6631156802177429},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5833475589752197},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5270814299583435},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5195813179016113},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49670153856277466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42111748456954956},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06652012467384338}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9276139736175537},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8066279888153076},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7417469024658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379547357559204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6631156802177429},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5833475589752197},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5270814299583435},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5195813179016113},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49670153856277466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42111748456954956},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06652012467384338},{"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/aspaa.2009.5346517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2009.5346517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1557470594","https://openalex.org/W1880262756","https://openalex.org/W2042737139","https://openalex.org/W2113679114","https://openalex.org/W2135537007","https://openalex.org/W2141398670","https://openalex.org/W2159591770","https://openalex.org/W2171784699","https://openalex.org/W4231510805","https://openalex.org/W4239875977","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1197719229","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048","https://openalex.org/W1493012537"],"abstract_inverted_index":{"We":[0,24,45],"present":[1],"a":[2,47],"probabilistic":[3,48],"speaker":[4,59,85],"clustering":[5,30],"and":[6,57,64,78,82],"diarization":[7,10,86],"model.":[8],"Speaker":[9],"determines":[11],"ldquowho":[12],"spoke":[13],"whenrdquo":[14],"from":[15],"the":[16,29,53,70,76],"recorded":[17],"conversation":[18],"of":[19,22,31,40,55,80],"unknown":[20,38],"number":[21,39,54,77],"people.":[23],"formulate":[25],"this":[26],"problem":[27],"as":[28],"sequential":[32],"auditory":[33],"features":[34,79],"generated":[35],"by":[36],"an":[37],"latent":[41],"mixture":[42],"components":[43],"(speakers).":[44],"employ":[46],"model":[49,72],"which":[50],"automatically":[51],"estimates":[52],"speakers":[56,81],"time-varying":[58],"proportions.":[60],"Experiments":[61],"with":[62],"synthetic":[63],"real":[65],"sound":[66],"recordings":[67],"confirm":[68],"that":[69],"proposed":[71],"can":[73],"successfully":[74],"infer":[75],"obtained":[83],"better":[84],"results":[87],"than":[88],"conventional":[89],"models.":[90]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}