{"id":"https://openalex.org/W1535817944","doi":"https://doi.org/10.21437/eurospeech.2003-580","title":"Modeling duration patterns for speaker recognition","display_name":"Modeling duration patterns for speaker recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1535817944","doi":"https://doi.org/10.21437/eurospeech.2003-580","mag":"1535817944"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051405063","display_name":"Harry Bratt","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harry Bratt","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108508738","display_name":"Venkata Ramana Rao Gadde","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkata R.R. Gadde","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin Kajarekar","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin S. Kajarekar","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023103090","display_name":"Kemal S\u00f6nmez","orcid":"https://orcid.org/0000-0002-2816-6438"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kemal Sonmez","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046717231","display_name":"Anand Venkataraman","orcid":"https://orcid.org/0000-0001-6303-4820"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Venkataraman","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5056267912"],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":6.396,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96361583,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2017","last_page":"2020"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/speech-recognition","display_name":"Speech recognition","score":0.8094913959503174},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.784899890422821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433294057846069},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6403613686561584},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6001458168029785},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.529836893081665},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5262393355369568},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.5217096209526062},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48817211389541626},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4863482117652893},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4859980046749115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4652707576751709},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.409224271774292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09685859084129333},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06617629528045654}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8094913959503174},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.784899890422821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433294057846069},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6403613686561584},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6001458168029785},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.529836893081665},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5262393355369568},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.5217096209526062},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48817211389541626},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4863482117652893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4859980046749115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652707576751709},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.409224271774292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09685859084129333},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06617629528045654},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W205402702","https://openalex.org/W2069883713","https://openalex.org/W2097978681","https://openalex.org/W2112882007","https://openalex.org/W2114851258","https://openalex.org/W2166637769"],"related_works":["https://openalex.org/W2606551632","https://openalex.org/W2153098279","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4229940372","https://openalex.org/W4250904811","https://openalex.org/W2104528589"],"abstract_inverted_index":{"We":[0,51,102],"present":[1],"a":[2,27,68,75,114],"method":[3],"for":[4],"speaker":[5,17,60,116],"recognition":[6,117],"that":[7,71,104],"uses":[8],"the":[9,33,36,41,44,49,53,87,95,99,125,135,146],"duration":[10,148],"patterns":[11],"of":[12,31,35,57,67,78],"speech":[13],"units":[14],"to":[15,85,138],"aid":[16],"classification.":[18],"The":[19,59],"approach":[20,106],"represents":[21],"each":[22],"word":[23],"and/or":[24],"phone":[25],"by":[26,93],"feature":[28],"vector":[29],"comprised":[30],"either":[32],"durations":[34],"individual":[37],"phones":[38],"making":[39,47],"up":[40,48],"word,":[42],"or":[43],"HMM":[45],"states":[46],"phone.":[50],"model":[52,70],"vectors":[54],"using":[55],"mixtures":[56],"Gaussians.":[58],"specific":[61],"models":[62,81],"are":[63,82,91],"obtained":[64,97],"through":[65],"adaptation":[66],"\u201cbackground\u201d":[69],"is":[72],"trained":[73],"on":[74,120],"large":[76],"pool":[77],"speakers.":[79],"Speaker":[80],"then":[83],"used":[84],"score":[86],"test":[88,142,147],"data;":[89],"they":[90],"normalized":[92],"subtracting":[94],"scores":[96],"with":[98,113,131,140],"background":[100],"model.":[101],"find":[103],"this":[105],"yields":[107],"significant":[108],"perfomance":[109],"improvement":[110,126,136],"when":[111],"combined":[112],"state-of-the-art":[115],"system":[118,152],"based":[119],"standard":[121,151],"cepstral":[122],"features.":[123,133],"Furthermore,":[124],"persists":[127],"even":[128],"after":[129],"combination":[130],"lexical":[132],"Finally,":[134],"continues":[137],"increase":[139],"longer":[141],"sample":[143],"durations,":[144],"beyond":[145],"at":[149],"which":[150],"accuracy":[153],"level":[154],"off.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}