{"id":"https://openalex.org/W2804119478","doi":"https://doi.org/10.1109/icassp.2018.8462416","title":"Measuring Uncertainty in Deep Regression Models: The Case of Age Estimation from Speech","display_name":"Measuring Uncertainty in Deep Regression Models: The Case of Age Estimation from Speech","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2804119478","doi":"https://doi.org/10.1109/icassp.2018.8462416","mag":"2804119478"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5071702566","display_name":"Nanxin Chen","orcid":"https://orcid.org/0000-0001-6698-1604"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nanxin Chen","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644900","display_name":"Yishay Carmiel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishay Carmiel","raw_affiliation_strings":["IntelligentWire, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"IntelligentWire, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071702566"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04956795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":null,"first_page":"4939","last_page":"4943"},"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":0.9995999932289124,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.7376536130905151},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6841696500778198},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5804941654205322},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5625067353248596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5504945516586304},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.540444016456604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5355349183082581},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5120204091072083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5075620412826538},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5023338794708252},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5002155303955078},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47874563932418823},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4320528507232666},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3873555660247803},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32095932960510254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27723824977874756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1617661416530609},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07551902532577515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376536130905151},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6841696500778198},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5804941654205322},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5625067353248596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504945516586304},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.540444016456604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5355349183082581},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5120204091072083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5075620412826538},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5023338794708252},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5002155303955078},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47874563932418823},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4320528507232666},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3873555660247803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32095932960510254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27723824977874756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1617661416530609},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07551902532577515},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1006777433","https://openalex.org/W1522301498","https://openalex.org/W1963783625","https://openalex.org/W2057563799","https://openalex.org/W2059673175","https://openalex.org/W2064675550","https://openalex.org/W2085628288","https://openalex.org/W2095705004","https://openalex.org/W2111959010","https://openalex.org/W2121029939","https://openalex.org/W2150769028","https://openalex.org/W2398521502","https://openalex.org/W2400670753","https://openalex.org/W2401809795","https://openalex.org/W2402268235","https://openalex.org/W2510616059","https://openalex.org/W2510637384","https://openalex.org/W2514741789","https://openalex.org/W2587150483","https://openalex.org/W4295095967","https://openalex.org/W6674330103","https://openalex.org/W6713098461","https://openalex.org/W6713109006"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2539884462","https://openalex.org/W2735628018"],"abstract_inverted_index":{"Age":[0],"estimation":[1,40,102],"from":[2],"speech":[3],"recently":[4],"received":[5],"a":[6,37,60,92,105,137],"lot":[7],"of":[8,30,44,50,75,107,119,163],"attention.":[9],"Approaches":[10],"such":[11],"as":[12],"i-vectors":[13],"and":[14,100,156,179],"deep":[15],"learning":[16],"have":[17],"been":[18],"successfully":[19],"applied":[20],"to":[21,58,95,136,152],"this":[22,88],"task":[23],"achieving":[24],"great":[25],"performance.":[26],"However,":[27],"one":[28],"drawback":[29],"those":[31],"methods":[32],"is":[33,66,79,113],"that":[34],"they":[35],"produce":[36],"hard":[38],"age":[39,99,155],"without":[41],"any":[42],"kind":[43],"confidence":[45,61],"measure":[46,62],"about":[47,63],"the":[48,51,56,73,98,121,147,153,157,161,164],"quality":[49],"prediction.":[52,165],"Designing":[53],"systems":[54],"with":[55],"ability":[57],"provide":[59],"their":[64],"output":[65,134],"extremely":[67],"valuable":[68],"for":[69,129],"several":[70],"applications":[71],"where":[72],"cost":[74],"making":[76,82],"bad":[77],"decisions":[78],"worse":[80],"than":[81],"no":[83],"decision,":[84],"e.g.,":[85],"forensics.":[86],"In":[87],"paper,":[89],"we":[90],"propose":[91],"novel":[93],"framework":[94],"jointly":[96],"predict":[97],"its":[101],"uncertainty":[103,162],"in":[104],"context":[106],"neural":[108,142],"regression":[109,130],"model.":[110],"This":[111],"model":[112],"trained":[114],"using":[115,120],"probabilistic":[116,133],"fashion":[117],"instead":[118],"classical":[122],"minimum":[123],"mean":[124,149],"square":[125],"error":[126],"objective":[127],"used":[128],"tasks.":[131],"The":[132,140],"corresponds":[135,151],"Gaussian":[138],"posterior.":[139],"proposed":[141],"network":[143],"will":[144],"estimate":[145],"both":[146],"posterior":[148],"which":[150,159],"predicted":[154],"variance":[158],"quantifies":[160],"We":[166],"evaluated":[167],"our":[168],"approach":[169],"on":[170],"two":[171],"different":[172],"datasets":[173],"NIST":[174],"SRE":[175],"2008":[176],"-":[177],"2010":[178],"Switchboard.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}