{"id":"https://openalex.org/W2140672401","doi":"https://doi.org/10.1109/icme.2003.1221388","title":"Location based speaker segmentation","display_name":"Location based speaker segmentation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2140672401","doi":"https://doi.org/10.1109/icme.2003.1221388","mag":"2140672401"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/82825","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/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":true,"raw_author_name":"G. Lathoud","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","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":"I.A. McCowan","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007555019"],"corresponding_institution_ids":["https://openalex.org/I2614128279"],"apc_list":null,"apc_paid":null,"fwci":5.6296,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.96947428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"III","last_page":"621"},"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":0.9993000030517578,"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":0.8371158838272095},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6831583976745605},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.680991530418396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6705231666564941},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6009803414344788},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6005649566650391},{"id":"https://openalex.org/keywords/whiteboard","display_name":"Whiteboard","score":0.5352839231491089},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5269889235496521},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5167319178581238},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4482024312019348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4416542053222656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.401089072227478},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3124857544898987},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14969784021377563},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08673056960105896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371158838272095},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6831583976745605},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.680991530418396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6705231666564941},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6009803414344788},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6005649566650391},{"id":"https://openalex.org/C2780315633","wikidata":"https://www.wikidata.org/wiki/Q16354","display_name":"Whiteboard","level":2,"score":0.5352839231491089},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5269889235496521},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5167319178581238},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4482024312019348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4416542053222656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.401089072227478},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3124857544898987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14969784021377563},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08673056960105896},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icme.2003.1221388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.8724","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.8724","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/~mccowan/pdf/lathoud-icassp2003.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.370.3947","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.3947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2003/segmentation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.3007","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.3007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.idiap.ch/pub/reports/2002/rr-02-43.ps.gz","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82825","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82825","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"},{"id":"pmh:oai:infoscience.epfl.ch:82871","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82871","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.epfl.ch:82825","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82825","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"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1555217905","https://openalex.org/W1558276682","https://openalex.org/W1591300715","https://openalex.org/W1946893126","https://openalex.org/W2046317813","https://openalex.org/W2108248087","https://openalex.org/W2111339787","https://openalex.org/W2114863372","https://openalex.org/W2125222651","https://openalex.org/W2172070182","https://openalex.org/W3143559350","https://openalex.org/W6628911050","https://openalex.org/W6633191483","https://openalex.org/W6635532411","https://openalex.org/W6677383040"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W1977167953","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,29,38,42,55,64,83,124],"technique":[4],"that":[5,66,128],"segments":[6],"audio":[7,93],"according":[8,48,94],"to":[9,28,49,74,86,95,103,149],"speakers":[10],"based":[11],"on":[12,120],"their":[13],"location.":[14,96],"In":[15,44],"many":[16],"multi-party":[17],"conversations,":[18],"such":[19,34,45,108],"as":[20,35,72,109],"meetings,":[21],"the":[22,92,110,118,129,144],"location":[23,131],"of":[24,32,58,91,112,146],"participants":[25],"is":[26],"restricted":[27],"small":[30],"number":[31],"regions,":[33],"seats":[36],"around":[37],"table,":[39],"or":[40],"at":[41],"whiteboard.":[43],"cases,":[46],"segmentation":[47,90],"these":[50],"discrete":[51],"regions":[52],"would":[53],"be":[54],"reliable":[56],"means":[57],"determining":[59],"speaker":[60,76],"turns.":[61],"We":[62],"propose":[63],"system":[65,119],"uses":[67],"microphone":[68],"pair":[69],"time":[70],"delays":[71],"features":[73,79,132],"represent":[75],"locations.":[77],"These":[78],"are":[80],"integrated":[81],"in":[82],"GMM/HMM":[84],"framework":[85,99],"determine":[87],"an":[88,147],"optimal":[89],"The":[97],"HMM":[98],"also":[100,142],"allows":[101],"extensions":[102],"recognize":[104],"more":[105],"complex":[106],"structure,":[107],"presence":[111],"two":[113],"simultaneous":[114],"speakers.":[115],"Experiments":[116],"testing":[117],"real":[121],"recordings":[122],"from":[123],"meeting":[125],"room":[126],"show":[127],"proposed":[130],"can":[133],"provide":[134],"greater":[135],"discrimination":[136],"than":[137],"standard":[138],"cepstral":[139],"features,":[140],"and":[141],"demonstrate":[143],"success":[145],"extension":[148],"handle":[150],"dual-speaker":[151],"overlap.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
