{"id":"https://openalex.org/W2100030705","doi":"https://doi.org/10.1109/icassp.2004.1326006","title":"Benefits of prior acoustic segmentation for automatic speaker segmentation","display_name":"Benefits of prior acoustic segmentation for automatic speaker segmentation","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2100030705","doi":"https://doi.org/10.1109/icassp.2004.1326006","mag":"2100030705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01434305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075235121","display_name":"Sylvain Meignier","orcid":"https://orcid.org/0000-0001-7687-073X"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"S. Meignier","raw_affiliation_strings":["LIA-Avignon, Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA-Avignon, Avignon, France","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002321802","display_name":"Daniel Moraru","orcid":"https://orcid.org/0000-0002-8087-8344"},"institutions":[{"id":"https://openalex.org/I177483745","display_name":"Universit\u00e9 Joseph Fourier","ror":"https://ror.org/02aj0kh94","country_code":"FR","type":"education","lineage":["https://openalex.org/I177483745"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"D. Moraru","raw_affiliation_strings":["CLIPS-IMAG(UJF and CNRS), Grenoble, France","Laboratoire d'Informatique de Grenoble [2007-2015]"],"affiliations":[{"raw_affiliation_string":"CLIPS-IMAG(UJF and CNRS), Grenoble, France","institution_ids":["https://openalex.org/I177483745","https://openalex.org/I899635006","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique de Grenoble [2007-2015]","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018458807","display_name":"Corinne Fredouille","orcid":"https://orcid.org/0000-0002-0413-8950"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Fredouille","raw_affiliation_strings":["LIA-Avignon, Avignon, France","Laboratoire Informatique d'Avignon"],"affiliations":[{"raw_affiliation_string":"LIA-Avignon, Avignon, France","institution_ids":["https://openalex.org/I4210119991"]},{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107853186","display_name":"Laurent Besacier","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I177483745","display_name":"Universit\u00e9 Joseph Fourier","ror":"https://ror.org/02aj0kh94","country_code":"FR","type":"education","lineage":["https://openalex.org/I177483745"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"L. Besacier","raw_affiliation_strings":["CLIPS-IMAG(UJF and CNRS), Grenoble, France","Laboratoire d'Informatique de Grenoble [2007-2015]"],"affiliations":[{"raw_affiliation_string":"CLIPS-IMAG(UJF and CNRS), Grenoble, France","institution_ids":["https://openalex.org/I177483745","https://openalex.org/I899635006","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique de Grenoble [2007-2015]","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080870411","display_name":"Jean-Fran\u00e7ois Bonastre","orcid":"https://orcid.org/0000-0001-7741-3346"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.F. Bonastre","raw_affiliation_strings":["LIA-Avignon, Avignon, France","Laboratoire Informatique d'Avignon"],"affiliations":[{"raw_affiliation_string":"LIA-Avignon, Avignon, France","institution_ids":["https://openalex.org/I4210119991"]},{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075235121"],"corresponding_institution_ids":["https://openalex.org/I4210119991"],"apc_list":null,"apc_paid":null,"fwci":5.3965,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95575652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9876999855041504,"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/segmentation","display_name":"Segmentation","score":0.8603345155715942},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8082451820373535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8024344444274902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7409933805465698},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.702867329120636},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.559902548789978},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.523837149143219},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5079033970832825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5067330002784729},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5055105686187744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.465986430644989},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.4653312563896179},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4217904508113861},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07997611165046692}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8603345155715942},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8082451820373535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024344444274902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7409933805465698},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.702867329120636},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.559902548789978},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.523837149143219},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5079033970832825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5067330002784729},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5055105686187744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.465986430644989},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.4653312563896179},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4217904508113861},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07997611165046692},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01434305v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01434305","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":"International Conference on Acoustics Speech and Signal Processing (ICASSP 2004), May 2004, Montreal, Canada. pp.397-400, ⟨10.1109/ICASSP.2004.1326006⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01434305v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01434305","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":"International Conference on Acoustics Speech and Signal Processing (ICASSP 2004), May 2004, Montreal, Canada. pp.397-400, ⟨10.1109/ICASSP.2004.1326006⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W110483337","https://openalex.org/W2016243284","https://openalex.org/W2063415950","https://openalex.org/W2079008574","https://openalex.org/W2149402184","https://openalex.org/W2170695863","https://openalex.org/W2399255709","https://openalex.org/W6712478597"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W2125642021","https://openalex.org/W2144208207","https://openalex.org/W2099333848"],"abstract_inverted_index":{"The":[0,22],"paper":[1],"investigates":[2],"the":[3,19,38,47,57,64,75,85,103,109,112,138,148],"interest":[4],"of":[5,24,33,41,66,96,111,133],"segmentation":[6,28,87,98],"in":[7,31,37,56,70,108,131],"acoustic":[8,27,68,125],"macro":[9],"classes":[10],"(like":[11],"gender":[12],"or":[13],"bandwidth)":[14],"as":[15],"front-end":[16],"processing":[17],"for":[18],"segmentation/diarization":[20],"task.":[21,88],"impact":[23],"this":[25],"prior":[26,67,124],"is":[29,53,135],"evaluated":[30],"terms":[32,132],"speaker":[34,86,97,153],"diarization":[35],"performance":[36],"particular":[39],"context":[40],"NIST":[42],"RT'03":[43],"evaluation":[44],"(done":[45],"on":[46,137,142,152],"HUB4":[48],"broadcast":[49],"news":[50],"corpora).":[51],"It":[52],"rarely":[54],"discussed":[55],"literature,":[58],"but":[59],"our":[60],"work":[61],"shows":[62],"that":[63],"application":[65],"segmentation,":[69],"a":[71,128],"similar":[72],"way":[73],"to":[74,84,147],"automatic":[76],"speech":[77],"recognition":[78],"task,":[79],"may":[80],"be":[81],"very":[82],"useful":[83],"Experiments":[89],"were":[90],"conducted":[91],"using":[92],"two":[93],"different":[94],"kinds":[95],"systems":[99],"developed":[100],"individually":[101],"by":[102],"LIA":[104,139],"and":[105],"CLIPS":[106,149],"laboratories":[107],"framework":[110],"ELISA":[113],"consortium.":[114],"For":[115],"both":[116],"systems,":[117],"improvement":[118],"was":[119],"observed":[120,136],"when":[121],"combined":[122],"with":[123],"segmentation.":[126],"However,":[127],"larger":[129],"impact,":[130],"performance,":[134],"system":[140,150],"based":[141,151],"an":[143],"ascending/HMM":[144],"approach":[145],"compared":[146],"turn":[154],"detection.":[155]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}