{"id":"https://openalex.org/W3174465459","doi":"https://doi.org/10.18260/1-2--36365","title":"Child vs Adult Speaker Diarization of naturalistic audio recordings in preschool environment using Deep Neural Networks","display_name":"Child vs Adult Speaker Diarization of naturalistic audio recordings in preschool environment using Deep Neural Networks","publication_year":2024,"publication_date":"2024-02-08","ids":{"openalex":"https://openalex.org/W3174465459","doi":"https://doi.org/10.18260/1-2--36365","mag":"3174465459"},"language":"en","primary_location":{"id":"doi:10.18260/1-2--36365","doi":"https://doi.org/10.18260/1-2--36365","is_oa":true,"landing_page_url":"https://doi.org/10.18260/1-2--36365","pdf_url":"https://peer.asee.org/36365.pdf","source":{"id":"https://openalex.org/S7407086954","display_name":"ASEE Gulf Southwest Section Conference","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ASEE 2021 Gulf-Southwest Annual Conference Proceedings","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://peer.asee.org/36365.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017818279","display_name":"Prasanna V. Kothalkar","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"]},{"id":"https://openalex.org/I169877490","display_name":"University of Mumbai","ror":"https://ror.org/032hdk172","country_code":"IN","type":"education","lineage":["https://openalex.org/I169877490"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Prasanna Kothalkar","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX, USA","degree in Computer Engineering from Mumbai University, Mumbai, India in 2010,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"degree in Computer Engineering from Mumbai University, Mumbai, India in 2010,","institution_ids":["https://openalex.org/I169877490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047277727","display_name":"Jay F. Buzhardt","orcid":"https://orcid.org/0000-0003-4634-3183","observed_orcids":["https://orcid.org/0000-0003-4634-3183"]},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]},{"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":"Jay Buzhardt","raw_affiliation_strings":["Juniper Garden's Children Project University of Kansas , KS , USA","Center for Robust Speech Systems (CRSS) University of Texas at Dallas, TX, USA","degree in Computer Science from University of Texas at Dallas, Dallas, United States, in 2014"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Juniper Garden's Children Project University of Kansas , KS , USA","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS) University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"degree in Computer Science from University of Texas at Dallas, Dallas, United States, in 2014","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","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/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]},{"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 Hansen","raw_affiliation_strings":["University of Texas at Dallas","Jonsson School of Engineering and Computer Science, University of Texas at Dallas (UTD), Richardson, United States","School of Behavioral & Brain Sciences (Speech & Hearing). At UTDallas, he established Center for Robust Speech Systems (CRSS)","University of Kansas, Dr"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Jonsson School of Engineering and Computer Science, University of Texas at Dallas (UTD), Richardson, United States","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"School of Behavioral & Brain Sciences (Speech & Hearing). At UTDallas, he established Center for Robust Speech Systems (CRSS)","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"University of Kansas, Dr","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005913278","display_name":"Dwight Irvin","orcid":"https://orcid.org/0000-0002-2324-7124","observed_orcids":["https://orcid.org/0000-0002-2324-7124"]},"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":"Dwight Irvin","raw_affiliation_strings":["Juniper Gardens Children's Project","Center for Robust Speech Systems (CRSS) University of Texas at Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Juniper Gardens Children's Project","institution_ids":[]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS) University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044954274","display_name":"Beth Rous","orcid":"https://orcid.org/0000-0002-4707-9022","observed_orcids":["https://orcid.org/0000-0002-4707-9022"]},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]},{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beth Rous","raw_affiliation_strings":["University of Kentucky","Juniper Garden's Children Project University of Kansas, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky","institution_ids":["https://openalex.org/I143302722"]},{"raw_affiliation_string":"Juniper Garden's Children Project University of Kansas, KS, USA","institution_ids":["https://openalex.org/I146416000"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00097173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9678000211715698,"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":0.9678000211715698,"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":0.01119999960064888,"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/T12031","display_name":"Speech and dialogue systems","score":0.010900000110268593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9959999918937683},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.6489999890327454},{"id":"https://openalex.org/keywords/early-childhood-education","display_name":"early childhood education","score":0.5239999890327454},{"id":"https://openalex.org/keywords/implementation-science","display_name":"implementation science","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7088284492492676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691616952419281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6684156060218811},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5782397985458374},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31786924600601196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31465548276901245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18260/1-2--36365","doi":"https://doi.org/10.18260/1-2--36365","is_oa":true,"landing_page_url":"https://doi.org/10.18260/1-2--36365","pdf_url":"https://peer.asee.org/36365.pdf","source":{"id":"https://openalex.org/S7407086954","display_name":"ASEE Gulf Southwest Section Conference","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ASEE 2021 Gulf-Southwest Annual Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18260/1-2--36365","doi":"https://doi.org/10.18260/1-2--36365","is_oa":true,"landing_page_url":"https://doi.org/10.18260/1-2--36365","pdf_url":"https://peer.asee.org/36365.pdf","source":{"id":"https://openalex.org/S7407086954","display_name":"ASEE Gulf Southwest Section Conference","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ASEE 2021 Gulf-Southwest Annual Conference Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1169669067","display_name":"Collaborative Research: CSL-MultiAD: Assessing Collaborative STEM Learning through Rich Information Flow based on Multi-Sensor Audio Diarization","funder_award_id":"1918012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4925320186","display_name":"Collaborative Research: CSL-MultiAD: Assessing Collaborative STEM Learning through Rich Information Flow based on Multi-Sensor Audio Diarization","funder_award_id":"1918032","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332210","display_name":"Institute of Education Sciences","ror":"https://ror.org/04et59085"},{"id":"https://openalex.org/F4320337604","display_name":"National Institute on Disability, Independent Living, and Rehabilitation Research","ror":"https://ror.org/033jnv181"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174465459.pdf","grobid_xml":"https://content.openalex.org/works/W3174465459.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1528954144","https://openalex.org/W1936725236","https://openalex.org/W2023098317","https://openalex.org/W2069620976","https://openalex.org/W2189248916","https://openalex.org/W2399733683","https://openalex.org/W2407501792","https://openalex.org/W2525241666","https://openalex.org/W2587150483","https://openalex.org/W2802488037","https://openalex.org/W2807627734","https://openalex.org/W2887814324","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2901616798","https://openalex.org/W2915887922","https://openalex.org/W2937267585","https://openalex.org/W2973193289","https://openalex.org/W2973896964","https://openalex.org/W3031133340","https://openalex.org/W4298742451","https://openalex.org/W6983383401"],"related_works":["https://openalex.org/W3176718666","https://openalex.org/W4414712375","https://openalex.org/W2972559945","https://openalex.org/W6982570116","https://openalex.org/W2973193289","https://openalex.org/W2404363352","https://openalex.org/W4402111540","https://openalex.org/W7067818648","https://openalex.org/W4415432890","https://openalex.org/W7047544855"],"abstract_inverted_index":{"Abstract":[0],"Speech":[1,72],"and":[2,19,43,69,233,237,247],"language":[3],"development":[4],"in":[5,13,47,60,88,97,103,208,218],"children":[6,62],"are":[7],"crucial":[8],"for":[9,57,83,121,136,149,211],"ensuring":[10],"effective":[11],"skills":[12],"their":[14,65,239],"long":[15],"term":[16],"learning":[17,40,101],"ability":[18,78],"the":[20,30,77,104,115,158,249],"person's":[21],"life-long":[22],"educational":[23],"journey.":[24],"A":[25,118],"child's":[26],"vocabulary":[27],"size":[28],"at":[29],"time":[31],"of":[32,39,123,152,189,251],"kindergarten":[33],"entry":[34],"is":[35,52,95,160],"an":[36],"early":[37,222],"indicator":[38],"to":[41,79],"read":[42],"potential":[44,206],"long-term":[45],"success":[46],"school.":[48],"The":[49],"preschool":[50,116],"classroom":[51,150],"thus":[53],"a":[54,98,219],"promising":[55],"venue":[56],"monitoring":[58],"growth":[59],"young":[61],"by":[63,114],"measuring":[64],"interactions":[66,151,240],"with":[67,241],"teachers":[68,231],"classmates.":[70],"Automatic":[71],"Recognition":[73],"(ASR)":[74],"technologies":[75],"provide":[76],"'Early":[80],"Childhood'":[81],"researchers":[82],"automatically":[84],"analyzing":[85],"naturalistic":[86,220],"recordings":[87,126],"these":[89],"settings.":[90],"For":[91],"this":[92],"purpose,":[93],"data":[94],"collected":[96],"high-quality":[99],"childcare":[100],"center":[102],"United":[105],"States":[106],"using":[107],"Language":[108],"Environment":[109],"Analysis":[110],"(LENA)":[111],"devices":[112],"worn":[113],"children.":[117,156],"preliminary":[119],"task":[120],"ASR":[122],"daylong":[124],"audio":[125],"would":[127],"involve":[128],"diarization":[129,147,164,181,203],"i.e.":[130],"segmenting":[131],"speech":[132,168],"into":[133],"smaller":[134],"parts":[135],"identifying":[137],"'who":[138],"spoke":[139],"when'.":[140],"This":[141],"study":[142],"investigates":[143],"different":[144],"Deep":[145],"Learning-based":[146],"systems":[148,182,204],"3-5":[153],"year":[154],"old":[155],"However,":[157],"focus":[159],"on":[161],"'speaker":[162],"group'":[163],"which":[165],"includes":[166],"classifying":[167],"segments":[169],"being":[170],"from":[171,175],"adults":[172],"or":[173,213],"children,":[174,242],"across":[176],"multiple":[177],"classrooms.":[178],"SincNet":[179],"based":[180],"achieve":[183],"utterance":[184],"level":[185,192],"Diarization":[186],"Error":[187],"Rate":[188],"21.6%.":[190],"Utterance":[191],"speaker":[193],"group":[194],"confusion":[195],"matrices":[196],"also":[197,229],"show":[198],"promising,":[199],"balanced":[200],"results.":[201],"These":[202],"have":[205],"applications":[207],"developing":[209],"metrics":[210],"adult-to-child":[212],"child-to-child":[214],"rapid":[215],"conversational":[216],"turns":[217],"noisy":[221],"childhood":[223],"setting.":[224],"Such":[225],"technical":[226],"advancements":[227],"will":[228],"help":[230],"better":[232],"more":[234],"efficiently":[235],"quantify":[236],"understand":[238],"make":[243],"changes":[244],"as":[245],"needed,":[246],"monitor":[248],"impact":[250],"those":[252],"changes.":[253]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2021-07-05T00:00:00"}
