{"id":"https://openalex.org/W2169264834","doi":"https://doi.org/10.1109/icassp.2008.4518619","title":"Overlapped speech detection for improved speaker diarization in multiparty meetings","display_name":"Overlapped speech detection for improved speaker diarization in multiparty meetings","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2169264834","doi":"https://doi.org/10.1109/icassp.2008.4518619","mag":"2169264834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518619","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 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/A5050639290","display_name":"Kofi Boakye","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kofi Boakye","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097382202","display_name":"Beatriz Trueba-Hornero","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Beatriz Trueba-Hornero","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Polytechnic University of Catalonia, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Polytechnic University of Catalonia, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Vinyals","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050639290"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":10.8435,"has_fulltext":false,"cited_by_count":122,"citation_normalized_percentile":{"value":0.99338624,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4353","last_page":"4356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9948999881744385,"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/headset","display_name":"Headset","score":0.9122820496559143},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.850049614906311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767333984375},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6315847635269165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6290481090545654},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.627342939376831},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5199557542800903},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5119177103042603},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4513288736343384},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41259509325027466},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3990585207939148},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34365013241767883},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20995444059371948}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.9122820496559143},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.850049614906311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767333984375},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6315847635269165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6290481090545654},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.627342939376831},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5199557542800903},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5119177103042603},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4513288736343384},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41259509325027466},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3990585207939148},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34365013241767883},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20995444059371948},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2008.4518619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518619","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.4727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.4727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/~vinyals/icassp08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.190.9991","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.9991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/boakye_icassp08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1558276682","https://openalex.org/W2115483887","https://openalex.org/W2124332251","https://openalex.org/W2163704482","https://openalex.org/W2338994564","https://openalex.org/W6659344013"],"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":{"State-of-the-art":[0],"speaker":[1],"diarization":[2,101],"systems":[3],"for":[4,47,61,104],"meetings":[5],"are":[6],"now":[7],"at":[8],"a":[9,56,71,84,91],"point":[10],"where":[11],"overlapped":[12,34],"speech":[13],"contributes":[14],"significantly":[15],"to":[16],"the":[17,21,64,74,79,99,105,110],"errors":[18],"made":[19],"by":[20],"system.":[22],"However,":[23],"little":[24],"if":[25],"no":[26],"work":[27,40],"has":[28],"yet":[29],"been":[30],"done":[31],"on":[32,58,70],"detecting":[33],"speech.":[35],"We":[36,51,119],"present":[37],"our":[38],"initial":[39,129],"toward":[41],"developing":[42],"an":[43],"overlap":[44],"detection":[45],"system":[46],"improved":[48],"meeting":[49],"diarization.":[50],"investigate":[52],"various":[53],"features,":[54],"with":[55],"focus":[57],"high-precision":[59],"performance":[60,68],"use":[62],"in":[63],"detector,":[65],"and":[66,125],"examine":[67],"results":[69],"subset":[72],"of":[73,83,94,109],"AMI":[75],"Meeting":[76],"Corpus.":[77],"For":[78],"high-quality":[80],"signal":[81,114],"case":[82,108],"single":[85,111],"mixed-headset":[86],"channel":[87,113],"signal,":[88],"we":[89],"demonstrate":[90],"relative":[92,115],"improvement":[93,116,124],"about":[95],"7.4%":[96],"DER":[97],"over":[98],"baseline":[100],"system,":[102],"while":[103],"more":[106],"challenging":[107],"far-field":[112],"is":[117],"3.6%.":[118],"also":[120],"outline":[121],"steps":[122],"towards":[123],"moving":[126],"beyond":[127],"this":[128],"phase.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":16}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
