{"id":"https://openalex.org/W2130708324","doi":"https://doi.org/10.1109/icassp.2012.6288842","title":"Low-latency speaker diarization based on Bayesian information criterion with multiple phoneme classes","display_name":"Low-latency speaker diarization based on Bayesian information criterion with multiple phoneme classes","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2130708324","doi":"https://doi.org/10.1109/icassp.2012.6288842","mag":"2130708324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5069525167","display_name":"Takahiro Oku","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takahiro Oku","raw_affiliation_strings":["NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109470000","display_name":"Shoei Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoei Sato","raw_affiliation_strings":["NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079042022","display_name":"Akio Kobayashi","orcid":"https://orcid.org/0000-0002-6927-7353"},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akio Kobayashi","raw_affiliation_strings":["NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063442191","display_name":"Shinichi Homma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichi Homma","raw_affiliation_strings":["NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055934853","display_name":"Toru Imai","orcid":"https://orcid.org/0009-0006-6715-7346"},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Imai","raw_affiliation_strings":["NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069525167"],"corresponding_institution_ids":["https://openalex.org/I4210107548"],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73208167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"4189","last_page":"4192"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9848999977111816,"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":0.9395267963409424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8014468550682068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7651848793029785},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6439249515533447},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5925374031066895},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5745800733566284},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4707149863243103},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4556962549686432},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.41813692450523376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31281083822250366},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06350794434547424}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9395267963409424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8014468550682068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651848793029785},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6439249515533447},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5925374031066895},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5745800733566284},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4707149863243103},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4556962549686432},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.41813692450523376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31281083822250366},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06350794434547424},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W9688279","https://openalex.org/W21371201","https://openalex.org/W1482605500","https://openalex.org/W1943968395","https://openalex.org/W2026144026","https://openalex.org/W2041695853","https://openalex.org/W2120735223","https://openalex.org/W2164031777","https://openalex.org/W2395438212","https://openalex.org/W4245490569","https://openalex.org/W6628911050","https://openalex.org/W6640709233","https://openalex.org/W6656616308","https://openalex.org/W6684028345"],"related_works":["https://openalex.org/W2119836628","https://openalex.org/W2206035908","https://openalex.org/W2356325859","https://openalex.org/W106647055","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2157299333"],"abstract_inverted_index":{"Low-latency":[0],"speaker":[1,7,35,45,74,103,122],"diarization":[2,36,75,99,104],"is":[3,83],"desirable":[4],"for":[5],"online-oriented":[6],"adaptation":[8,123],"in":[9,14,28,76,125],"real-time":[10],"speech":[11],"recognition.":[12],"Especially":[13],"spontaneous":[15],"conversations,":[16],"several":[17],"speakers":[18],"tend":[19],"to":[20,111],"speak":[21],"alternatively":[22],"and":[23,42],"continuously":[24,85],"without":[25],"any":[26],"silence":[27],"between":[29],"utterances.":[30],"We":[31],"therefore":[32],"propose":[33],"a":[34,47,55,116,126],"method":[37,100],"that":[38],"detects":[39],"speaker-change":[40,134],"points":[41,135],"determines":[43],"the":[44,52,71,77,81,102,112],"with":[46,115],"fixed":[48],"low":[49,78],"latency":[50,79],"on":[51,93],"basis":[53],"of":[54,73],"Bayesian":[56],"information":[57],"criterion":[58],"(BIC)":[59],"by":[60,108,137],"using":[61],"acoustic":[62],"features":[63],"classified":[64],"into":[65],"multiple":[66],"phoneme":[67,88,118],"classes.":[68],"To":[69],"improve":[70],"accuracy":[72],"condition,":[80],"speaker-decision":[82],"made":[84],"at":[86,133],"each":[87],"boundary.":[89],"In":[90],"an":[91],"experiment":[92,128],"conversational":[94],"broadcast":[95],"news":[96],"programs,":[97],"our":[98],"reduced":[101,129],"error":[105,131],"rate":[106,132],"relatively":[107,136],"20.0%":[109],"compared":[110],"conventional":[113],"BIC":[114],"single":[117],"class.":[119],"The":[120],"online":[121],"applied":[124],"speech-recognition":[127],"word":[130],"7.8%.":[138]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}