{"id":"https://openalex.org/W1519129566","doi":"https://doi.org/10.21437/interspeech.2010-427","title":"Bayes factor based speaker segmentation for speaker diarization","display_name":"Bayes factor based speaker segmentation for speaker diarization","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1519129566","doi":"https://doi.org/10.21437/interspeech.2010-427","mag":"1519129566"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-427","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/40855/1/40855.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072315089","display_name":"D. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"D. Wang","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109041704","display_name":"Robert Vogt","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Robert Vogt","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072315089"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.929,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79280825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1405","last_page":"1408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9984999895095825,"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":0.9955999851226807,"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":0.9438275098800659},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.718510091304779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6852009296417236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6470621824264526},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6001416444778442},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.52813321352005},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5176487565040588},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.4851261079311371},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47249045968055725},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.46961313486099243},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4386691749095917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3978721499443054},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.17723718285560608},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06412455439567566}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9438275098800659},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.718510091304779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852009296417236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6470621824264526},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6001416444778442},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.52813321352005},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5176487565040588},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4851261079311371},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47249045968055725},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.46961313486099243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4386691749095917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3978721499443054},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.17723718285560608},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06412455439567566},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-427","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:40855","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/40855/1/40855.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 11th Annual Conference of the International Speech Communication Association","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:40855","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/40855/1/40855.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 11th Annual Conference of the International Speech Communication Association","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1519129566.pdf","grobid_xml":"https://content.openalex.org/works/W1519129566.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W604181985","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W2008957275","https://openalex.org/W2111418533","https://openalex.org/W2117812871","https://openalex.org/W2119836628","https://openalex.org/W2157005274","https://openalex.org/W2166980079","https://openalex.org/W2911964094","https://openalex.org/W4230941884","https://openalex.org/W4301264738"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2537862391","https://openalex.org/W4247736853","https://openalex.org/W2417174640","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"the":[3,6,34,37,41,45,51,70,90,97],"use":[4],"of":[5,27,36],"Bayes":[7,38],"Factor":[8,39],"as":[9],"a":[10,17,25,77,85],"distance":[11],"metric":[12],"for":[13],"speaker":[14,18,78],"segmentation":[15,60],"within":[16],"diarization":[19,79],"system.":[20],"The":[21],"proposed":[22],"approach":[23,82],"uses":[24],"pair":[26],"constant":[28],"sized,":[29],"sliding":[30],"windows":[31,43],"to":[32,63,96],"compute":[33],"value":[35],"between":[40],"adjacent":[42],"over":[44],"entire":[46],"audio.":[47],"Results":[48],"obtained":[49],"on":[50],"2002":[52],"Rich":[53],"Transcription":[54],"Evaluation":[55],"dataset":[56],"show":[57],"an":[58],"improved":[59],"performance":[61],"compared":[62,95],"previous":[64],"approaches":[65],"reported":[66],"in":[67,76,84,89],"literature":[68],"using":[69],"Generalized":[71],"Likelihood":[72],"Ratio.":[73],"When":[74],"applied":[75],"system,":[80],"this":[81],"results":[83],"5.1%":[86],"relative":[87],"improvement":[88],"overall":[91],"Diarization":[92],"Error":[93],"Rate":[94],"baseline.":[98]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}