{"id":"https://openalex.org/W4367276802","doi":"https://doi.org/10.1121/10.0018568","title":"End-to-end child-adult speech diarization in naturalistic conditions of preschool classrooms","display_name":"End-to-end child-adult speech diarization in naturalistic conditions of preschool classrooms","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4367276802","doi":"https://doi.org/10.1121/10.0018568"},"language":"en","primary_location":{"id":"doi:10.1121/10.0018568","doi":"https://doi.org/10.1121/10.0018568","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1121/10.0018568","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prasanna V. Kothalkar","raw_affiliation_strings":["Ctr. for Robust Speech Systems, Univ. of Texas at Dallas, 800 W Campbell Rd., Erik Jonsson School of Eng., EC32 P.O. Box 830688, Richardson, TX 75080-3021, Prasanna.Kothalkar@utdallas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ctr. for Robust Speech Systems, Univ. of Texas at Dallas, 800 W Campbell Rd., Erik Jonsson School of Eng., EC32 P.O. Box 830688, Richardson, TX 75080-3021, Prasanna.Kothalkar@utdallas.edu","institution_ids":["https://openalex.org/I162577319"]}]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dwight Irvin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Buzhardt","raw_affiliation_strings":["Juniper Gardens Childrens Project, Univ. of Kansas, Kansas City, KS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Juniper Gardens Childrens Project, Univ. of Kansas, Kansas City, KS","institution_ids":["https://openalex.org/I146416000"]}]},{"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. Hansen","raw_affiliation_strings":["CRSS: Ctr. for Robust Speech Systems, Univ. of Texas - Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRSS: Ctr. for Robust Speech Systems, Univ. of Texas - Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017818279"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"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":"153","issue":"3_supplement","first_page":"A174","last_page":"A174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9848999977111816,"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":0.9848999977111816,"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":0.00930000003427267,"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":0.00279999990016222,"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/speaker-diarization","display_name":"speaker diarization","score":0.9359999895095825},{"id":"https://openalex.org/keywords/preschool-classrooms","display_name":"preschool classrooms","score":0.9330000281333923},{"id":"https://openalex.org/keywords/ecapa-tdnn","display_name":"ECAPA-TDNN","score":0.8349999785423279},{"id":"https://openalex.org/keywords/early-childhood-communication","display_name":"early childhood communication","score":0.5450000166893005},{"id":"https://openalex.org/keywords/audio-segmentation","display_name":"audio segmentation","score":0.6439999938011169},{"id":"https://openalex.org/keywords/educational-assessment","display_name":"educational assessment","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.703214168548584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5830148458480835},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46629565954208374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4473051428794861},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40973180532455444},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2482122778892517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23372432589530945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/10.0018568","doi":"https://doi.org/10.1121/10.0018568","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1121/10.0018568","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6164000034332275}],"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/W4391733873","https://openalex.org/W4367022905","https://openalex.org/W3141174088","https://openalex.org/W6893154889","https://openalex.org/W4312459597","https://openalex.org/W4408353371","https://openalex.org/W7160937726","https://openalex.org/W2889288729","https://openalex.org/W3006898571","https://openalex.org/W4309321049"],"abstract_inverted_index":{"Speech":[0],"and":[1,10,32,40,75,87,150,191,196],"language":[2],"development":[3],"are":[4,19,46],"early":[5,56],"indicators":[6],"of":[7,34,49,55,63,102,139,165,177,193],"overall":[8],"analytical":[9],"learning":[11],"ability":[12],"in":[13,21],"pre-school":[14],"children.":[15],"Early":[16],"childhood":[17,57],"researchers":[18],"interested":[20],"analyzing":[22],"naturalistic":[23,168],"versus":[24],"controlled":[25],"lab":[26],"recordings":[27],"to":[28,61,79,122],"assess":[29],"both":[30,189],"quality":[31],"quantity":[33],"such":[35],"communication":[36,183],"interactions":[37,101],"between":[38],"children":[39,105,195],"adults/teachers.":[41],"Unfortunately,":[42],"present-day":[43],"speech":[44,118],"technologies":[45],"not":[47],"capable":[48],"addressing":[50,178],"the":[51,110,175],"wide":[52],"dynamic":[53],"scenario":[54],"classroom":[58,100,170],"settings.":[59],"Due":[60],"diversity":[62],"acoustic":[64],"events/conditionsin":[65],"daylong":[66],"audio":[67,85,184],"streams,":[68],"automated":[69],"speaker":[70,160],"diarization":[71,96,115],"technology":[72],"is":[73,112],"limited":[74],"must":[76],"be":[77],"advanced":[78],"address":[80],"this":[81],"challenging":[82],"domain":[83],"for":[84,98,153,158],"segmentation":[86],"meta-data":[88],"information":[89],"extraction.":[90],"We":[91],"investigate":[92],"a":[93,136,163],"Deep":[94],"Learning-based":[95],"solution":[97],"segmenting":[99],"3\u20135":[103],"year-old":[104],"engaging":[106],"with":[107],"teachers.":[108],"Here,":[109],"focus":[111],"on":[113,141,147],"speaker-label":[114],"which":[116],"classifies":[117],"segments":[119],"as":[120],"belonging":[121],"either":[123],"Adults":[124],"or":[125],"Children,":[126],"partitioned":[127],"across":[128,167],"multiple":[129],"classrooms.":[130],"Our":[131],"proposed":[132],"ECAPA-TDNN":[133],"model":[134],"achieves":[135],"best":[137],"F1-score":[138],"65.5%":[140],"data":[142],"from":[143],"two":[144],"classrooms,":[145],"based":[146],"open":[148],"dev":[149],"test":[151],"sets":[152],"each":[154],"classroom.":[155],"Also,":[156],"F1-scores":[157],"individual":[159],"labels":[161],"provide":[162],"breakdown":[164],"performance":[166],"child":[169],"engagement.":[171],"The":[172],"study":[173],"demonstrates":[174],"prospects":[176],"educational":[179],"assessment":[180],"needs":[181],"through":[182],"stream":[185],"analysis,":[186],"while":[187],"maintaining":[188],"security":[190],"privacy":[192],"all":[194],"adults.":[197]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2023-04-29T00:00:00"}