{"id":"https://openalex.org/W1542328173","doi":null,"title":"Test token driven acoustic balancing for sparse enrollment data in cohort GMM speaker recognition","display_name":"Test token driven acoustic balancing for sparse enrollment data in cohort GMM speaker recognition","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1542328173","mag":"1542328173"},"language":"en","primary_location":{"id":"mag:1542328173","doi":null,"is_oa":false,"landing_page_url":"https://apps.dtic.mil/dtic/tr/fulltext/u2/a517221.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363607788","display_name":"European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference","raw_type":null},"volume":null,"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jun-Won Suh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Won Suh","raw_affiliation_strings":["[Center for Robust Speech Systems (CRSS) Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, Texas, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Center for Robust Speech Systems (CRSS) Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, Texas, USA]","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["[Center for Robust Speech Systems (CRSS) Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, Texas, USA]"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"[Center for Robust Speech Systems (CRSS) Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, Texas, USA]","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04377264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"572","last_page":"575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0006000000284984708,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.7279999852180481},{"id":"https://openalex.org/keywords/limited-test-data","display_name":"limited test data","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932026743888855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6388698220252991},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.6147866249084473},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.591249942779541},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5454847812652588},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5133656859397888},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5004298686981201},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.491328626871109},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.45040565729141235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4268803000450134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35987389087677},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:1542328173","doi":null,"is_oa":false,"landing_page_url":"https://apps.dtic.mil/dtic/tr/fulltext/u2/a517221.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363607788","display_name":"European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W25107353","https://openalex.org/W1532575630","https://openalex.org/W2008957275","https://openalex.org/W2041823554","https://openalex.org/W2123838014","https://openalex.org/W2136880172","https://openalex.org/W2148484850","https://openalex.org/W2165108269"],"related_works":["https://openalex.org/W1977769820","https://openalex.org/W2520765863","https://openalex.org/W132035425","https://openalex.org/W7095107019","https://openalex.org/W2166717394","https://openalex.org/W2150748440","https://openalex.org/W1801988848","https://openalex.org/W4389073804","https://openalex.org/W25107353","https://openalex.org/W2156265451"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"address":[4],"the":[5,40,44,61,66,75,91,94,102,119,128,153,177,194],"problem":[6],"of":[7,26,98],"sparse":[8,223],"train/test":[9],"data":[10,17,116,126,146,161,225],"for":[11,221],"in-set/out-of-set":[12],"speaker":[13,62],"recognition.":[14],"Sparse":[15],"enrollment":[16,137,158,224],"presents":[18],"a":[19,24,56,216],"unique":[20],"challenge":[21],"due":[22],"to":[23,59,219],"lack":[25],"acoustic":[27,36,41,83,95,134,148,155],"space":[28],"coverage.":[29],"The":[30,139,167,185,211],"proposed":[31,212],"algorithm":[32,213],"focuses":[33],"on":[34,188],"filling":[35],"holes":[37],"and":[38,79,90,159,196,226],"fortifying":[39],"information":[42,64,150],"using":[43,55,74,101,107,132,172,206],"claimed":[45],"speaker's":[46],"test":[47,99,115,125,145,160,209,228],"token":[48,96,100],"histogram.":[49],"This":[50],"scheme":[51],"is":[52,85,104,170,215],"possible":[53],"by":[54],"GMM":[57,70],"model":[58],"classify":[60],"phone":[63],"at":[65],"feature":[67,84],"level.":[68],"Parallel":[69],"training":[71],"with":[72,180],"EM":[73],"most":[76,120],"occurring":[77,81],"(top)":[78,122],"least":[80],"(bottom)":[82,142],"called":[86,105],"\u201cTop-Down":[87],"Bottom-Up":[88],"(TDBU)\u201d,":[89],"method":[92,169],"employing":[93],"histogram":[97,117],"TDBU":[103],"\u201cTDBU":[106],"Test":[108],"Token":[109],"Histogram":[110],"(TTH)\u201d.":[111],"Since":[112],"TTH":[113],"provides":[114],"information,":[118],"occurred":[121,141],"parts":[123],"in":[124,136,144,165],"fortify":[127],"its":[129],"discriminating":[130],"ability":[131],"same":[133],"tokens":[135],"data.":[138,210,229],"less":[140],"part":[143],"provide":[147],"hole":[149,156],"so":[151],"that":[152],"mismatched":[154],"between":[157],"can":[162],"be":[163],"filled":[164],"chance.":[166],"TDBU-TTH":[168,186],"evaluated":[171],"telephone":[173],"conversation":[174],"speech":[175],"from":[176],"FISHER":[178],"corpus":[179],"5":[181],"second":[182,208],"train":[183],"sets.":[184],"improves":[187],"average":[189,198],"2.17%":[190],"absolute":[191,200],"EER":[192,201],"over":[193,203],"TDBU,":[195],"an":[197],"4.03%":[199],"improvement":[202,214],"GMM-UBM":[204],"baseline":[205],"2":[207],"noteworthy":[217],"stage":[218],"compensate":[220],"both":[222],"limited":[227]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}