{"id":"https://openalex.org/W7163572269","doi":"https://doi.org/10.31234/osf.io/xca5j_v3","title":"Psychometric Validation of a Deep Learning-based Foreground Speech Detection Algorithm for Everyday Conversation Detection","display_name":"Psychometric Validation of a Deep Learning-based Foreground Speech Detection Algorithm for Everyday Conversation Detection","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163572269","doi":"https://doi.org/10.31234/osf.io/xca5j_v3"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/xca5j_v3","doi":"https://doi.org/10.31234/osf.io/xca5j_v3","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/xca5j_v3","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/xca5j_v3","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128329117","display_name":"Amanda Marie Bernal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amanda Marie Bernal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119585448","display_name":"Johannes Leonhard Klinz","orcid":"https://orcid.org/0000-0003-3454-7509","observed_orcids":["https://orcid.org/0000-0003-3454-7509"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johannes Leonhard Klinz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3454-7509","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024849291","display_name":"Valeria A. Pfeifer","orcid":"https://orcid.org/0000-0003-1252-5050","observed_orcids":["https://orcid.org/0000-0003-1252-5050"]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valeria Pfeifer","raw_affiliation_strings":["University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127833059","display_name":"David Sbarra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Sbarra","raw_affiliation_strings":["University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024726266","display_name":"Charles L. Raison","orcid":"https://orcid.org/0000-0001-6687-0066","observed_orcids":["https://orcid.org/0000-0001-6687-0066"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles L Raison","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6687-0066","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126295951","display_name":"Nicole Nugent","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicole Nugent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085315115","display_name":"Rajat Hebbar","orcid":"https://orcid.org/0000-0002-0904-0573","observed_orcids":["https://orcid.org/0000-0002-0904-0573"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajat Hebbar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126294751","display_name":"Shrikanth Narayanan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023882384","display_name":"Matthias R. Mehl","orcid":"https://orcid.org/0000-0003-2698-5007","observed_orcids":["https://orcid.org/0000-0003-2698-5007"]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias R. Mehl","raw_affiliation_strings":["University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.3837999999523163,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.3837999999523163,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.26170000433921814,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.093299999833107,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/environmental-sounds","display_name":"environmental sounds","score":0.7730000019073486},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.6700000166893005},{"id":"https://openalex.org/keywords/psychometric-validation","display_name":"psychometric validation","score":0.8090000152587891},{"id":"https://openalex.org/keywords/well-being","display_name":"well-being","score":0.8880000114440918},{"id":"https://openalex.org/keywords/personality","display_name":"personality","score":0.8259999752044678},{"id":"https://openalex.org/keywords/temporal-stability","display_name":"temporal stability","score":0.8510000109672546}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.9488999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656000018119812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48820000886917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45590001344680786},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45419999957084656},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C2779018934","wikidata":"https://www.wikidata.org/wiki/Q1129653","display_name":"Everyday life","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C65499552","wikidata":"https://www.wikidata.org/wiki/Q5421061","display_name":"Experience sampling method","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C187288502","wikidata":"https://www.wikidata.org/wiki/Q641118","display_name":"Personality","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/xca5j_v3","doi":"https://doi.org/10.31234/osf.io/xca5j_v3","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/xca5j_v3","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31234/osf.io/xca5j_v3","doi":"https://doi.org/10.31234/osf.io/xca5j_v3","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/xca5j_v3","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2068868050","https://openalex.org/W146392349","https://openalex.org/W3202889690","https://openalex.org/W2407934257","https://openalex.org/W109582023","https://openalex.org/W7034503769","https://openalex.org/W856085131","https://openalex.org/W7071426338","https://openalex.org/W4308600709","https://openalex.org/W3189585926"],"abstract_inverted_index":{"Passive":[0],"ambient":[1,64,222],"audio":[2,33,65,108],"sampling":[3],"bears":[4],"great":[5],"potential":[6],"for":[7,58,178,194,211],"objectively":[8,215],"measuring":[9],"daily":[10,217],"social":[11],"activity":[12,60,90,164,184,197],"and":[13,18,29,136,145,170,174,203],"its":[14],"association":[15],"with":[16,67,96,125],"wellbeing":[17],"health.":[19],"However,":[20],"detecting":[21],"true":[22],"conversations":[23],"via":[24,32],"human":[25,97,153,171],"annotation":[26],"is":[27,209],"labor-intensive,":[28],"automatic":[30],"labeling":[31],"signal":[34],"processing":[35],"has":[36],"thus":[37],"far":[38],"only":[39],"received":[40],"proof-of-concept":[41],"validation.":[42],"Here,":[43],"we":[44,111],"conduct":[45],"a":[46,51,199],"comprehensive":[47],"psychometric":[48,192],"validation":[49],"of":[50,88,133,139,162,201],"deep":[52],"learning-based":[53],"foreground":[54],"speech":[55],"detection":[56,61],"algorithm":[57,123,169,189],"conversation":[59,89,99,127,134,163,183,196],"(CAD)":[62],"from":[63,152,166,219],"sampled":[66,221],"the":[68,80,114,117,121,159,167,180,187],"Electronically":[69],"Activated":[70],"Recorder":[71],"(EAR)":[72],"method":[73],"(Hebbar":[74],"et":[75],"al.,":[76],"2021).":[77],"We":[78,156],"assess":[79],"CAD":[81,122,168,188],"algorithm\u2019s":[82,181],"validity":[83],"as":[84],"an":[85],"objective":[86],"measure":[87,216],"using":[91],"four":[92,115],"archival":[93],"EAR":[94],"datasets":[95],"ground-truth":[98,154,172],"annotations":[100,173],"(N":[101],"=":[102,106],"566":[103],"participants,":[104],"n":[105],"167,539":[107],"recordings).":[109],"Specifically,":[110],"evaluate,":[112],"across":[113,198],"samples,":[116],"degree":[118],"to":[119,149,214],"which":[120],"converges":[124],"human-annotated":[126],"activity,":[128,135],"yields":[129],"temporal":[130],"stability":[131],"estimates":[132],"replicates":[137],"patterns":[138],"external":[140],"correlates":[141],"(with":[142],"demographic,":[143],"wellbeing,":[144],"personality":[146],"measures)":[147],"comparable":[148],"those":[150],"derived":[151,165],"annotations.":[155],"further":[157],"compare":[158],"distributional":[160],"properties":[161,193],"use":[175],"this":[176],"information":[177],"thresholding":[179],"continuous":[182],"estimates.":[185],"Overall,":[186],"evidences":[190],"strong":[191],"estimating":[195],"range":[200],"participants":[202],"study":[204],"characteristics,":[205],"suggesting":[206],"that":[207],"it":[208],"suitable":[210],"at-scale":[212],"deployment":[213],"socializing":[218],"passively":[220],"audio.":[223]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-05T00:00:00"}