{"id":"https://openalex.org/W2116475748","doi":"https://doi.org/10.1109/icassp.2002.5743671","title":"Speaker detection and tracking for telephone transactions","display_name":"Speaker detection and tracking for telephone transactions","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2116475748","doi":"https://doi.org/10.1109/icassp.2002.5743671","mag":"2116475748"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743671","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5111855509","display_name":"Jack McLaughlin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack McLaughlin","raw_affiliation_strings":["Applied Physics Laboratory, Univ. of Washington, Seattle, WA","Applied Physics Laboratory, University of Washington, Seattle 98105, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Physics Laboratory, Univ. of Washington, Seattle, WA","institution_ids":["https://openalex.org/I4210138199"]},{"raw_affiliation_string":"Applied Physics Laboratory, University of Washington, Seattle 98105, USA","institution_ids":["https://openalex.org/I4210138199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112042504","display_name":"Douglas A. Reynolds","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas A. Reynolds","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA","MIT Lincoln Laboratory, Lexington, MA 02420-9185, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA 02420-9185, USA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18278146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"I","last_page":"129"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958000183105469,"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":0.8431791663169861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7341148853302002},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.705470085144043},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.679945170879364},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6731364727020264},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6609618663787842},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5017504692077637},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.447769433259964},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44008970260620117},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43827611207962036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37342387437820435},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33394068479537964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431791663169861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7341148853302002},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.705470085144043},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.679945170879364},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6731364727020264},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6609618663787842},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5017504692077637},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.447769433259964},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44008970260620117},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43827611207962036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37342387437820435},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33394068479537964},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743671","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.3171","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.3171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ll.mit.edu/mission/communications/ist/publications/020513_McLaughlin.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W42176576","https://openalex.org/W76945434","https://openalex.org/W85845213","https://openalex.org/W97107628","https://openalex.org/W1482605500","https://openalex.org/W1547083988","https://openalex.org/W2105852083","https://openalex.org/W6601744818","https://openalex.org/W6603105437","https://openalex.org/W6604007911","https://openalex.org/W6628911050","https://openalex.org/W6632910081"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"As":[0,191],"ever":[1],"greater":[2],"numbers":[3],"of":[4,65,113,150,172,176,188,207],"telephone":[5,177],"transactions":[6],"are":[7,107,167,215],"being":[8],"conducted":[9],"solely":[10],"between":[11],"a":[12,48,131,135,143,170],"caller":[13],"and":[14,28,46,52,62,81,87,115,141,163,205,218],"an":[15,36,184],"automated":[16],"answering":[17],"system,":[18],"the":[19,33,59,66,82,95,110,120,148,151,154,164,173,202,208,227],"need":[20,34],"increases":[21],"for":[22,35,158,194],"software":[23],"which":[24,56,224],"can":[25],"automatically":[26],"identify":[27],"authenticate":[29],"these":[30],"callers":[31],"without":[32],"onerous":[37],"speaker":[38,50,68,73,78,137,203],"enrollment":[39,61],"process.":[40],"In":[41,71],"this":[42,72],"paper":[43],"we":[44],"introduce":[45],"investigate":[47],"novel":[49],"detection":[51,162,182],"tracking":[53],"(SDT)":[54],"technique,":[55],"dynamically":[57],"merges":[58],"traditional":[60],"recognition":[63,69,74],"phases":[64],"static":[67],"task.":[70,156],"application,":[75],"no":[76],"prior":[77],"models":[79],"exist":[80],"goal":[83],"is":[84,124,196],"to":[85,109,126,146,220,225],"detect":[86],"model":[88],"new":[89,144],"speakers":[90,106,114,118],"as":[91],"they":[92],"call":[93],"into":[94],"system":[96,132,140,152,228],"while":[97],"also":[98],"recognizing":[99],"utterances":[100],"from":[101,117],"previously":[102],"modeled":[103],"callers.":[104],"New":[105],"added":[108],"enrolled":[111,122],"set":[112,123,204],"speech":[116,178],"in":[119,223],"currently":[121],"used":[125],"update":[127],"models.":[128],"We":[129],"describe":[130],"based":[133],"on":[134,153,201],"GMM":[136],"identification":[138],"(SID)":[139],"develop":[142],"measure":[145],"evaluate":[147],"performance":[149,193],"SDT":[155,165,195],"Results":[157],"both":[159],"static,":[160],"open-set":[161,181],"task":[166],"presented":[168],"using":[169],"portion":[171],"Switchboard":[174],"corpus":[175],"communications.":[179],"Static":[180],"produces":[183],"equal":[185],"error":[186],"rate":[187],"about":[189],"5%.":[190],"expected,":[192],"quite":[197,216],"varied,":[198],"depending":[199],"greatly":[200],"ordering":[206],"test":[209],"sequence.":[210],"These":[211],"initial":[212],"results,":[213],"however,":[214],"promising":[217],"point":[219],"potential":[221],"areas":[222],"improve":[226],"performance.":[229]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}