{"id":"https://openalex.org/W2004709066","doi":"https://doi.org/10.1109/icassp.2013.6639169","title":"Speaker diarization using data-driven audio sequencing","display_name":"Speaker diarization using data-driven audio sequencing","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2004709066","doi":"https://doi.org/10.1109/icassp.2013.6639169","mag":"2004709066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639169","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":"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/A5109134626","display_name":"Houssemeddine Khemiri","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I4387153010","display_name":"Telecom SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]},{"id":"https://openalex.org/I4405261500","display_name":"Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux","ror":"https://ror.org/05d29yv45","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010","https://openalex.org/I4405261500"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Houssemeddine Khemiri","raw_affiliation_strings":["Institut Mines-T\u00e9l\u00e9com; CNRS LTCI, CNRS SAMOVAR, T\u00e9l\u00e9com ParisTech, France","CNRS - Centre National de la Recherche Scientifique (France)","TSI - D\u00e9partement Traitement du Signal et des Images (T\u00e9l\u00e9com ParisTech / TSI 46, rue Barrault 75634 PARIS Cedex 13 - France)","TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","SAMOVAR - Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux (T\u00e9l\u00e9com Sudparis, 9 rue Charles Fourier -91011 Evry cedex - France)"],"affiliations":[{"raw_affiliation_string":"Institut Mines-T\u00e9l\u00e9com; CNRS LTCI, CNRS SAMOVAR, T\u00e9l\u00e9com ParisTech, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I205703379","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"TSI - D\u00e9partement Traitement du Signal et des Images (T\u00e9l\u00e9com ParisTech / TSI 46, rue Barrault 75634 PARIS Cedex 13 - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"SAMOVAR - Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux (T\u00e9l\u00e9com Sudparis, 9 rue Charles Fourier -91011 Evry cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4405261500","https://openalex.org/I4387153010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025002731","display_name":"Dijana Petrovska\u2010Delacr\u00e9taz","orcid":"https://orcid.org/0000-0001-6485-2972"},"institutions":[{"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/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4387153010","display_name":"Telecom SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]},{"id":"https://openalex.org/I4405261500","display_name":"Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux","ror":"https://ror.org/05d29yv45","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010","https://openalex.org/I4405261500"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dijana Petrovska-Delacretaz","raw_affiliation_strings":["Institut Mines-T\u00e9l\u00e9com; CNRS SAMOVAR, T\u00e9l\u00e9com ParisTech, France","CNRS - Centre National de la Recherche Scientifique (France)","TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","SAMOVAR - Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux (T\u00e9l\u00e9com Sudparis, 9 rue Charles Fourier -91011 Evry cedex - France)"],"affiliations":[{"raw_affiliation_string":"Institut Mines-T\u00e9l\u00e9com; CNRS SAMOVAR, T\u00e9l\u00e9com ParisTech, France","institution_ids":["https://openalex.org/I205703379","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]},{"raw_affiliation_string":"SAMOVAR - Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux (T\u00e9l\u00e9com Sudparis, 9 rue Charles Fourier -91011 Evry cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4405261500","https://openalex.org/I4387153010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054175637","display_name":"G\u00e9rard Chollet","orcid":"https://orcid.org/0000-0003-4245-146X"},"institutions":[{"id":"https://openalex.org/I120156002","display_name":"Boise State University","ror":"https://ror.org/02e3zdp86","country_code":"US","type":"education","lineage":["https://openalex.org/I120156002"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Gerard Chollet","raw_affiliation_strings":["TELECOM ParisTech, Paris, \u00c3\u017dle-de-France, FR","Boise State University (1910 University Drive, Boise, Idaho 83725 - United States)","TSI - D\u00e9partement Traitement du Signal et des Images (T\u00e9l\u00e9com ParisTech / TSI 46, rue Barrault 75634 PARIS Cedex 13 - France)","LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)"],"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech, Paris, \u00c3\u017dle-de-France, FR","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Boise State University (1910 University Drive, Boise, Idaho 83725 - United States)","institution_ids":["https://openalex.org/I120156002"]},{"raw_affiliation_string":"TSI - D\u00e9partement Traitement du Signal et des Images (T\u00e9l\u00e9com ParisTech / TSI 46, rue Barrault 75634 PARIS Cedex 13 - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109134626"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912","https://openalex.org/I4387153010","https://openalex.org/I4405261500"],"apc_list":null,"apc_paid":null,"fwci":0.9576,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73960408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"7736","last_page":"7740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9994999766349792,"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":0.8987517952919006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794571042060852},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7470269203186035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7051339149475098},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6964653730392456},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5299813747406006},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4979135990142822},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.464446097612381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4641040563583374},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4202979803085327},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4042821228504181},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3533811569213867}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8987517952919006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794571042060852},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7470269203186035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7051339149475098},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6964653730392456},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5299813747406006},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4979135990142822},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.464446097612381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641040563583374},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4202979803085327},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4042821228504181},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3533811569213867},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639169","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-01275106v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01275106","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2013 : 38th IEEE International Conference on Acoustics, Speech and Signal Processing, May 2013, Vancouver, Canada. pp.7736 - 7740, &#x27E8;10.1109/ICASSP.2013.6639169&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W77717145","https://openalex.org/W163807827","https://openalex.org/W1482605500","https://openalex.org/W1578701839","https://openalex.org/W1647671624","https://openalex.org/W2055043387","https://openalex.org/W2069342299","https://openalex.org/W2081074144","https://openalex.org/W2134383396","https://openalex.org/W2158358098","https://openalex.org/W2176632294","https://openalex.org/W2620757702","https://openalex.org/W4236236547","https://openalex.org/W6602944679","https://openalex.org/W6628911050","https://openalex.org/W6634452667","https://openalex.org/W6636915900","https://openalex.org/W6738902873"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W4234190324","https://openalex.org/W2162158162","https://openalex.org/W2545131480","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"In":[0,13],"this":[1],"paper,":[2],"a":[3,22,86],"speaker":[4],"diarization":[5],"system":[6,49,75],"based":[7],"on":[8,34],"data-driven":[9],"segmentation":[10,18,59],"is":[11,37,41,60],"proposed.":[12],"addition":[14],"to":[15,63],"the":[16,30,45,65,79,96],"usual":[17],"and":[19,71,84],"clustering":[20],"steps,":[21],"new":[23],"module":[24],"which":[25,50,94],"detects":[26],"repeated":[27],"segments":[28,51,68],"between":[29],"same":[31],"shows":[32],"broadcasted":[33],"different":[35],"dates":[36],"added.":[38],"This":[39],"process":[40],"achieved":[42],"by":[43],"using":[44],"ALISP-based":[46],"audio":[47,52,67],"identification":[48],"data":[53],"into":[54],"pseudo-phonetic":[55],"units.":[56],"The":[57,74],"ALISP":[58],"then":[61],"used":[62],"identify":[64],"similar":[66],"in":[69],"TV":[70],"radio":[72],"shows.":[73],"was":[76,95],"evaluated":[77],"during":[78],"ETAPE":[80],"2011":[81],"evaluation":[82],"campaign":[83],"obtained":[85],"Diarization":[87],"Error":[88],"Rate":[89],"-":[90],"DER":[91],"of":[92],"16.23%":[93],"best":[97],"result":[98],"among":[99],"seven":[100],"participants.":[101]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
