{"id":"https://openalex.org/W2402499435","doi":"https://doi.org/10.21437/interspeech.2011-438","title":"Using speaker ID to discover repeat callers of a spoken dialog system","display_name":"Using speaker ID to discover repeat callers of a spoken dialog system","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2402499435","doi":"https://doi.org/10.21437/interspeech.2011-438","mag":"2402499435"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5008266542","display_name":"Andrew Fandrianto","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Fandrianto","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058756331","display_name":"Brian Langner","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Langner","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W. Black","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008266542"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32674642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1317","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9950000047683716,"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/dialog-box","display_name":"Dialog box","score":0.9337179660797119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8366996049880981},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6844611763954163},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6504665613174438},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5880990624427795},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.539443850517273},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5313886404037476},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5207090973854065},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4392751455307007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36957746744155884},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20260074734687805},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07243084907531738}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9337179660797119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366996049880981},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6844611763954163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6504665613174438},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5880990624427795},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.539443850517273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5313886404037476},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5207090973854065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4392751455307007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36957746744155884},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20260074734687805},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07243084907531738},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1508665521","https://openalex.org/W2339276216"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844"],"abstract_inverted_index":{"This":[0,91],"paper":[1],"describes":[2],"using":[3,16,68],"speaker":[4,156],"ID":[5,48,157],"techniques":[6],"to":[7,24,57,88,95],"identify":[8],"repeat":[9],"callers":[10,98,138],"in":[11,64,72,135,140,146],"a":[12,27,31,65,108,142,147],"spoken":[13,154],"dialog":[14,28,66,120],"system,":[15],"only":[17],"acoustic":[18,70],"features.":[19],"Often":[20],"it":[21,37],"is":[22,30,34,49,93,133],"useful":[23],"know":[25],"if":[26],"user":[29,62,102,125,144],"novice":[32],"or":[33,52,117],"experienced,":[35],"and":[36,99,139],"can":[38],"be":[39],"the":[40,69,73,77,113,119,124,131],"case":[41],"that":[42,130],"identifying":[43,141],"data":[44],"such":[45],"as":[46],"Caller":[47],"either":[50],"unreliable":[51],"unavailable.":[53],"Our":[54,127],"approach":[55],"attempts":[56],"remedy":[58],"this":[59],"by":[60,83],"determining":[61],"identity":[63],"session":[67],"information":[71],"dialog.":[74],"We":[75],"optimize":[76],"audio":[78],"content":[79],"of":[80,115,150],"each":[81],"call":[82],"removing":[84],"artifacts":[85],"not":[86],"relevant":[87],"modeling":[89],"speech.":[90],"technique":[92,132],"applied":[94],"finding":[96],"consecutive":[97,137],"creating":[100],"unique":[101,143],"identities":[103,145],"over":[104,107],"all":[105],"calls":[106],"larger":[109],"time":[110],"frame,":[111],"with":[112],"aim":[114],"tuning":[116],"adapting":[118],"system":[121],"based":[122],"on":[123],"identity.":[126],"results":[128],"show":[129],"effective":[134],"recognizing":[136],"large":[148],"set":[149],"calls.":[151],"Index":[152],"Terms:":[153],"dialog,":[155]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
