{"id":"https://openalex.org/W2009876684","doi":"https://doi.org/10.1109/icassp.2013.6639163","title":"Impact of overlapping speech detection on speaker diarization for broadcast news and debates","display_name":"Impact of overlapping speech detection on speaker diarization for broadcast news and debates","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2009876684","doi":"https://doi.org/10.1109/icassp.2013.6639163","mag":"2009876684"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01836475","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106430617","display_name":"Delphine Charlet","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Delphine Charlet","raw_affiliation_strings":["France Telecom, Orange Labs, Lannion, France","Orange Labs, France Telecom, Lannion, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"France Telecom, Orange Labs, Lannion, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs, France Telecom, Lannion, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112867496","display_name":"Claude Barras","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claude Barras","raw_affiliation_strings":["LIMSI-CNRS, Univ. Paris-Sud, Orsay, France","LIMSI, Univ. Paris-Sud, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Univ. Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"LIMSI, Univ. Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107173963","display_name":"Jean-Sylvain Li\u00e9nard","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Sylvain Lienard","raw_affiliation_strings":["LIMSI-CNRS, Univ. Paris-Sud, Orsay, France","LIMSI, Univ. Paris-Sud, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Univ. Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"LIMSI, Univ. Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7707","last_page":"7711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987000226974487,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7970420122146606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.738075315952301},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7075951099395752},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5156751871109009},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4579741656780243},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.44523459672927856},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4229260981082916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40658217668533325},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37615036964416504},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34403377771377563},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.28041160106658936}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7970420122146606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738075315952301},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7075951099395752},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5156751871109009},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4579741656780243},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.44523459672927856},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4229260981082916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40658217668533325},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37615036964416504},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34403377771377563},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28041160106658936},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01836475v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01836475","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2013, Vancouver, Canada. pp.7707-7711, ⟨10.1109/ICASSP.2013.6639163⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01836475v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01836475","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2013, Vancouver, Canada. pp.7707-7711, ⟨10.1109/ICASSP.2013.6639163⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W191366985","https://openalex.org/W1558276682","https://openalex.org/W1946893126","https://openalex.org/W2020150184","https://openalex.org/W2038959083","https://openalex.org/W2097583714","https://openalex.org/W2098441927","https://openalex.org/W2106103082","https://openalex.org/W2124078061","https://openalex.org/W2130950425","https://openalex.org/W2136745572","https://openalex.org/W2151572725","https://openalex.org/W2153994037","https://openalex.org/W2166980079","https://openalex.org/W2169264834","https://openalex.org/W2406713305","https://openalex.org/W2541366197","https://openalex.org/W4298871147","https://openalex.org/W6602944679","https://openalex.org/W6607850509","https://openalex.org/W6633191483","https://openalex.org/W6660288692","https://openalex.org/W6675718704","https://openalex.org/W6679204903","https://openalex.org/W6682345114","https://openalex.org/W6682965620","https://openalex.org/W6684823487","https://openalex.org/W6713701993","https://openalex.org/W6843904268"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1521049138","https://openalex.org/W1556857061"],"abstract_inverted_index":{"The":[0],"overlapping":[1,34,108],"speech":[2,35,55,72,109],"detection":[3,36],"systems":[4,110],"developped":[5],"by":[6],"Orange":[7],"and":[8,19,81,111,124],"LIMSI":[9],"for":[10,33,106],"the":[11,43,47,54,64,69,77,88,96,101,117],"ETAPE":[12,48],"evaluation":[13,49],"campaign":[14],"on":[15,42],"French":[16],"broadcast":[17],"news":[18,65],"debates":[20],"are":[21],"described.":[22],"Using":[23],"either":[24],"cepstral":[25],"features":[26],"or":[27],"a":[28,31],"multi-pitch":[29],"analysis,":[30],"F1-measure":[32],"up":[37,125],"to":[38,66,126],"59.2%":[39],"is":[40],"reported":[41],"TV":[44],"data":[45],"of":[46,53,103],"set,":[50],"where":[51],"6.7%":[52],"was":[56],"measured":[57],"as":[58],"overlapping,":[59],"ranging":[60],"from":[61],"1.2%":[62],"in":[63,68,121,129],"10.4%":[67],"debates.":[70],"Overlapping":[71],"segments":[73,83],"were":[74,84],"excluded":[75],"during":[76],"speaker":[78,91],"diarization":[79,118],"stage,":[80],"these":[82],"further":[85],"labelled":[86],"with":[87],"two":[89],"nearest":[90],"labels,":[92],"taking":[93],"into":[94],"account":[95],"temporal":[97],"distance.":[98],"We":[99],"describe":[100],"effects":[102],"this":[104],"strategy":[105],"various":[107],"we":[112],"show":[113],"that":[114],"it":[115],"improves":[116],"error":[119],"rate":[120],"all":[122],"situations":[123],"26.1%":[127],"relative":[128],"our":[130],"best":[131],"configuration.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}