{"id":"https://openalex.org/W3117312663","doi":"https://doi.org/10.23919/eusipco47968.2020.9287552","title":"Analysis of Phonetic Dependence of Segmentation Errors in Speaker Diarization","display_name":"Analysis of Phonetic Dependence of Segmentation Errors in Speaker Diarization","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3117312663","doi":"https://doi.org/10.23919/eusipco47968.2020.9287552","mag":"3117312663"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287552","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10044/1/80786","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043685273","display_name":"Simon W. McKnight","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Simon W. McKnight","raw_affiliation_strings":["Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031002666","display_name":"Aidan O. T. Hogg","orcid":"https://orcid.org/0000-0001-5501-7799"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aidan O. T. Hogg","raw_affiliation_strings":["Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043685273"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70167816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"385"},"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":0.9965999722480774,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9811999797821045,"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":0.9089716672897339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147760391235352},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6867626309394836},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.679620087146759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6625591516494751},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5671913623809814},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5320758819580078},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48239171504974365},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4382556974887848},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42901185154914856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3332101106643677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3225793242454529},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14091676473617554}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9089716672897339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147760391235352},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6867626309394836},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.679620087146759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6625591516494751},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5671913623809814},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5320758819580078},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48239171504974365},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4382556974887848},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42901185154914856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3332101106643677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3225793242454529},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14091676473617554},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287552","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/80786","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/80786","pdf_url":"http://hdl.handle.net/10044/1/80786","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference (EUSIPCO)","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/80786","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/80786","pdf_url":"http://hdl.handle.net/10044/1/80786","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference (EUSIPCO)","raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3117312663.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1590744681","https://openalex.org/W1903951673","https://openalex.org/W2077804127","https://openalex.org/W2081074144","https://openalex.org/W2103723258","https://openalex.org/W2121464381","https://openalex.org/W2125336414","https://openalex.org/W2155416917","https://openalex.org/W2155995145","https://openalex.org/W2889418727","https://openalex.org/W2972680151","https://openalex.org/W2997785206","https://openalex.org/W6605762983","https://openalex.org/W6635410338","https://openalex.org/W6675471587"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W2767892728","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W4247736853","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Evaluation":[0],"of":[1,9,39,68,102,123,136,157,160],"speaker":[2,15,21,44,51,57,161],"segmentation":[3,77],"and":[4,82,105,126,154],"diarization":[5,45,52,162],"normally":[6],"makes":[7],"use":[8,135],"forgiveness":[10,41,139],"collars":[11,26,42],"around":[12],"ground":[13,75],"truth":[14,76],"segment":[16,22,58],"boundaries":[17,23,92],"such":[18,25],"that":[19,34,54,73,107,133],"estimated":[20],"with":[24,93],"are":[27,87],"considered":[28],"completely":[29],"correct.":[30],"This":[31,96,143],"paper":[32],"shows":[33,106],"the":[35,64,74,99,113,119,129,134,149,158],"popular":[36],"recent":[37],"approach":[38],"removing":[40],"from":[43],"evaluation":[46],"tools":[47],"can":[48],"unfairly":[49],"penalize":[50],"systems":[53],"correctly":[55],"estimate":[56],"boundaries.":[59],"The":[60],"uncertainty":[61],"in":[62],"identifying":[63],"start":[65,120],"and/or":[66],"end":[67,122],"a":[69,137],"particular":[70],"phoneme":[71,91,100,114,130],"means":[72],"is":[78,117,141,145],"not":[79],"perfectly":[80],"accurate,":[81],"even":[83],"trained":[84],"human":[85],"listeners":[86],"unable":[88],"to":[89,147],"identify":[90],"full":[94],"consistency.":[95],"research":[97],"analyses":[98],"dependence":[101],"this":[103],"uncertainty,":[104],"it":[108],"depends":[109],"on":[110],"(i)":[111],"whether":[112],"being":[115],"detected":[116],"at":[118],"or":[121],"an":[124],"utterance":[125],"(ii)":[127],"what":[128],"is,":[131],"so":[132],"uniform":[138],"collar":[140],"inadequate.":[142],"analysis":[144],"expected":[146],"point":[148],"way":[150],"towards":[151],"more":[152],"indicative":[153],"repeatable":[155],"assessment":[156],"performance":[159],"systems.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}