{"id":"https://openalex.org/W1517127681","doi":"https://doi.org/10.21437/interspeech.2006-185","title":"Detection of a third speaker in telephone conversations","display_name":"Detection of a third speaker in telephone conversations","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W1517127681","doi":"https://doi.org/10.21437/interspeech.2006-185","mag":"1517127681"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-185","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001040819","display_name":"Uchechukwu O. Ofoegbu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uchechukwu O. Ofoegbu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113486419","display_name":"Ananth N. Iyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananth N. Iyer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058938449","display_name":"Robert E. Yantorno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert E. Yantorno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077493047","display_name":"Stanley J. Wenndt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stanley J. Wenndt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2214,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77096409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1133","last_page":"Wed3CaP.1"},"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":0.9998000264167786,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7963755130767822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497246265411377},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7274423241615295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7232804298400879},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5643688440322876},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5089654922485352},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47008848190307617},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.4513987898826599},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.425201952457428},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42386576533317566},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41057994961738586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34537604451179504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34341078996658325},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16193300485610962},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12907752394676208},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11063319444656372}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7963755130767822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497246265411377},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7274423241615295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7232804298400879},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5643688440322876},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5089654922485352},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47008848190307617},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4513987898826599},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.425201952457428},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42386576533317566},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41057994961738586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34537604451179504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34341078996658325},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16193300485610962},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12907752394676208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11063319444656372},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.21437/interspeech.2006-185","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1010.4290","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1010.4290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://works.bepress.com/iyer/8/download/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W85845213","https://openalex.org/W1482605500","https://openalex.org/W1499900670","https://openalex.org/W2103892053","https://openalex.org/W2123959143","https://openalex.org/W2130499067","https://openalex.org/W2162125266","https://openalex.org/W2165880886","https://openalex.org/W2166637769","https://openalex.org/W2485688913"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W1556857061"],"abstract_inverted_index":{"Differentiating":[0],"speakers":[1,39,60,78,201],"participating":[2,79,97],"in":[3,10,80,150,182],"telephone":[4,82,257],"conversations":[5,243],"is":[6,61,84,101,187,213,225],"a":[7,63,68,81,222],"challenging":[8,54],"task":[9,50],"speech":[11,152,212],"processing":[12],"because":[13],"only":[14,29],"short":[15,105],"consecutive":[16],"utterances":[17,31,106],"can":[18,37],"be":[19,135],"examined":[20],"for":[21,70],"each":[22,183],"speaker.":[23,120],"Research":[24],"has":[25],"shown":[26],"that,":[27],"given":[28],"brief":[30],"(1":[32],"second":[33],"or":[34,76,91,113,198],"less),":[35],"humans":[36],"recognize":[38],"with":[40],"an":[41,147,231],"accuracy":[42],"of":[43,95,123,174,179,210,235],"about":[44,58,93],"54":[45],"%":[46,237,250],"on":[47,103,203,240,255],"average.":[48],"The":[49,99,121,143,207,227],"becomes":[51],"even":[52],"more":[53],"when":[55,238,253],"no":[56,89],"information":[57,92],"the":[59,96,108,118,162,168,196,216,245],"known":[62],"priori.":[64],"In":[65],"this":[66,124],"paper,":[67],"technique":[69,100,229],"determining":[71],"whether":[72,112],"there":[73],"are":[74,158,165],"two":[75,155,192],"three":[77],"conversation":[83,109],"presented.":[85],"This":[86],"approach":[87],"assumes":[88],"knowledge":[90],"any":[94],"speakers.":[98],"based":[102,202],"comparing":[104],"within":[107],"and":[110,130,133,141,171,248],"deciding":[111],"not":[114],"they":[115],"belong":[116,194],"to":[117,137,189,195,199,219],"same":[119,197],"applications":[122],"research":[125],"include":[126],"3-way":[127],"call":[128],"detection":[129,140],"speaker":[131,138,224],"tracking,":[132],"could":[134],"extended":[136],"change-point":[139],"indexing.":[142],"proposed":[144,228],"method":[145],"involves":[146],"elimination":[148,217],"process":[149,218],"which":[151],"segments":[153,181],"matching":[154],"reference":[156],"models":[157,193],"sequentially":[159],"removed":[160],"from":[161,244],"conversation.":[163,184],"Models":[164],"formed":[166],"using":[167],"mean":[169],"vectors":[170],"covariance":[172],"matrices":[173],"Linear":[175],"Predictive":[176],"Cepstral":[177],"Coefficients":[178],"voiced":[180],"Hotelling\u2019s":[185],"T2-Statistic":[186],"used":[188],"determine":[190,220],"if":[191,221],"different":[200],"likelihood":[204],"ratio":[205],"testing.":[206],"relative":[208],"amount":[209],"residual":[211],"observed":[214],"after":[215],"third":[223],"present.":[226],"yielded":[230],"equal":[232],"error":[233,251],"rate":[234,252],"20":[236],"tested":[239,254],"artificially":[241],"simulated":[242],"HTIMIT":[246],"database":[247],"23":[249],"actual":[256],"conversations.":[258],"1.":[259]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}