{"id":"https://openalex.org/W1517146827","doi":"https://doi.org/10.21437/eurospeech.2003-47","title":"Segmenting multiple concurrent speakers using microphone arrays","display_name":"Segmenting multiple concurrent speakers using microphone arrays","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1517146827","doi":"https://doi.org/10.21437/eurospeech.2003-47","mag":"1517146827"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-47","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/82861/files/lathoud_eurospeech2003.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007555019","display_name":"Guillaume Lathoud","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Guillaume Lathoud","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Iain A. McCowan","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Intelligence (IDIAP) P. O. Box 592, CH-1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Intelligence (IDIAP) P. O. Box 592, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103546787","display_name":"Darren Moore","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Darren C. Moore","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Intelligence (IDIAP) P. O. Box 592, CH-1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Intelligence (IDIAP) P. O. Box 592, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7684,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95946999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2889","last_page":"2892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9994000196456909,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.829026460647583},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8118957877159119},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6398718357086182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6352224349975586},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5854421257972717},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.5505589842796326},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5150951743125916},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48480191826820374},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4508237838745117},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.44360843300819397},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44190889596939087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43051159381866455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4139205813407898},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07342717051506042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829026460647583},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8118957877159119},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6398718357086182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6352224349975586},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5854421257972717},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5505589842796326},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5150951743125916},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48480191826820374},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4508237838745117},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.44360843300819397},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44190889596939087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43051159381866455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4139205813407898},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07342717051506042},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/eurospeech.2003-47","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:82861","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82861","pdf_url":"https://infoscience.epfl.ch/record/82861/files/lathoud_eurospeech2003.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.2670","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.2670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/papers/2003/lathoud_eurospeech2003.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82856","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82856","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:82861","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82861","pdf_url":"https://infoscience.epfl.ch/record/82861/files/lathoud_eurospeech2003.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5699999928474426},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1517146827.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1558276682","https://openalex.org/W1591300715","https://openalex.org/W1946893126","https://openalex.org/W2046317813","https://openalex.org/W2114863372","https://openalex.org/W2140672401"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speaker":[0],"turn":[1],"detection":[2],"is":[3,28],"an":[4,87,116],"important":[5],"task":[6],"for":[7,120],"many":[8],"speech":[9],"processing":[10],"applications.":[11],"However,":[12,80],"accurate":[13],"segmentation":[14,67,118,142],"can":[15],"be":[16,103],"hard":[17],"to":[18],"achieve":[19],"if":[20],"there":[21],"are":[22,138],"multiple":[23],"concurrent":[24,100],"speakers":[25,101],"(overlap),":[26],"as":[27,43,74,76,95],"typically":[29],"the":[30,38,41,90,141,147],"case":[31],"in":[32,60,68],"multi-party":[33],"conversations.":[34],"In":[35,106],"such":[36,81],"cases,":[37],"location":[39],"of":[40,70,89,92,99],"speaker,":[42,122],"measured":[44],"using":[45,146],"a":[46,65,82],"microphone":[47],"array,":[48],"may":[49],"provide":[50],"greater":[51],"discrimination":[52],"than":[53],"traditional":[54],"spectral":[55],"features.":[56],"This":[57],"was":[58],"verified":[59],"previous":[61,148],"work":[62],"which":[63],"obtained":[64,145],"global":[66,83],"terms":[69],"single":[71],"speaker":[72,127],"classes,":[73,94],"well":[75],"possible":[77,97],"overlap":[78,93],"combinations.":[79,128],"strategy":[84],"suffers":[85],"from":[86],"explosion":[88],"number":[91],"each":[96,121],"combination":[98],"must":[102],"modeled":[104],"explicitly.":[105],"this":[107],"paper,":[108],"we":[109],"propose":[110],"two":[111],"alternative":[112],"schemes":[113],"that":[114,144],"produce":[115],"individual":[117],"decision":[119],"implicitly":[123],"handling":[124],"all":[125],"overlapping":[126],"The":[129],"proposed":[130],"approaches":[131],"also":[132],"allow":[133],"straightforward":[134],"online":[135],"implementations.":[136],"Experiments":[137],"presented":[139],"comparing":[140],"with":[143],"system.":[149],"1.":[150]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
