{"id":"https://openalex.org/W4415399178","doi":"https://doi.org/10.1109/icdl63968.2025.11204438","title":"Who Said What (WSW 2.0)? Enhanced Automated Analysis of Preschool Classroom Speech","display_name":"Who Said What (WSW 2.0)? Enhanced Automated Analysis of Preschool Classroom Speech","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415399178","doi":"https://doi.org/10.1109/icdl63968.2025.11204438"},"language":"en","primary_location":{"id":"doi:10.1109/icdl63968.2025.11204438","doi":"https://doi.org/10.1109/icdl63968.2025.11204438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204438","pdf_url":null,"source":{"id":"https://openalex.org/S7407087479","display_name":"IEEE International Conference on Development and Learning (ICDL)","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":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.09972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011063783","display_name":"Anchen Sun","orcid":"https://orcid.org/0000-0003-3633-6385","observed_orcids":["https://orcid.org/0000-0003-3633-6385"]},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anchen Sun","raw_affiliation_strings":["University of Miami,Department of Electrical and Computer Engineering,Coral Gables,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami,Department of Electrical and Computer Engineering,Coral Gables,FL,USA","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059679122","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068","observed_orcids":["https://orcid.org/0000-0002-2053-9068"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California,Viterbi School of Engineering,Department of Computer Science,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Viterbi School of Engineering,Department of Computer Science,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gabriela Gutierrez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriela Gutierrez","raw_affiliation_strings":["University of Miami,Department of Psychology,Coral Gables,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami,Department of Psychology,Coral Gables,FL,USA","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093734207","display_name":"Juan J Londono","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan J Londono","raw_affiliation_strings":["University of Miami,Department of Psychology,Coral Gables,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami,Department of Psychology,Coral Gables,FL,USA","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047152376","display_name":"Anfeng Xu","orcid":"https://orcid.org/0009-0001-5780-9797","observed_orcids":["https://orcid.org/0009-0001-5780-9797"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anfeng Xu","raw_affiliation_strings":["University of Southern California,Viterbi School of Engineering,Department of Computer Science,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Viterbi School of Engineering,Department of Computer Science,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086771138","display_name":"Batya E. Elbaum","orcid":"https://orcid.org/0000-0002-1257-8251","observed_orcids":["https://orcid.org/0000-0002-1257-8251"]},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Batya Elbaum","raw_affiliation_strings":["University of Miami,Department of Teaching and Learning,Coral Gables,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami,Department of Teaching and Learning,Coral Gables,FL,USA","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Shri Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204","observed_orcids":["https://orcid.org/0000-0002-1052-6204"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Viterbi School of Engineering,Department of Computer Science,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Viterbi School of Engineering,Department of Computer Science,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021426639","display_name":"Lynn K. Perry","orcid":"https://orcid.org/0000-0001-6976-3741","observed_orcids":["https://orcid.org/0000-0001-6976-3741"]},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lynn K Perry","raw_affiliation_strings":["University of Miami,Department of Psychology,Coral Gables,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami,Department of Psychology,Coral Gables,FL,USA","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063647797","display_name":"Daniel S. Messinger","orcid":"https://orcid.org/0000-0002-9551-675X","observed_orcids":["https://orcid.org/0000-0002-9551-675X"]},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S Messinger","raw_affiliation_strings":["University of Miami,Department of Psychology,Coral Gables,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami,Department of Psychology,Coral Gables,FL,USA","institution_ids":["https://openalex.org/I145608581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9768,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87573644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9545999765396118,"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":0.9545999765396118,"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/T10730","display_name":"Language Development and Disorders","score":0.010400000028312206,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T12031","display_name":"Speech and dialogue systems","score":0.008899999782443047,"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/vocal-interaction","display_name":"vocal interaction","score":0.4580000042915344},{"id":"https://openalex.org/keywords/speaker-classification","display_name":"speaker classification","score":0.8230000138282776},{"id":"https://openalex.org/keywords/speech-transcription","display_name":"speech transcription","score":0.8500000238418579},{"id":"https://openalex.org/keywords/teacher-child-interaction","display_name":"teacher-child interaction","score":0.5139999985694885},{"id":"https://openalex.org/keywords/early-language-development","display_name":"early childhood language development","score":0.7379999756813049},{"id":"https://openalex.org/keywords/utterance-length","display_name":"utterance length","score":0.75},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"lexical diversity","score":0.9490000009536743},{"id":"https://openalex.org/keywords/questioning","display_name":"questioning","score":0.9100000262260437},{"id":"https://openalex.org/keywords/automatic-speech-analysis","display_name":"automated speech analysis","score":0.49799999594688416}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5789999961853027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4553999900817871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C95975521","wikidata":"https://www.wikidata.org/wiki/Q6803628","display_name":"Mean length of utterance","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226999878883362},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4036000072956085},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C104709138","wikidata":"https://www.wikidata.org/wiki/Q1671540","display_name":"Intraclass correlation","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C2778073708","wikidata":"https://www.wikidata.org/wiki/Q2330667","display_name":"Language development","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204438","doi":"https://doi.org/10.1109/icdl63968.2025.11204438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204438","pdf_url":null,"source":{"id":"https://openalex.org/S7407087479","display_name":"IEEE International Conference on Development and Learning (ICDL)","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":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.09972","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.09972","pdf_url":"https://arxiv.org/pdf/2505.09972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.09972","doi":"https://doi.org/10.48550/arxiv.2505.09972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.09972","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.09972","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.09972","pdf_url":"https://arxiv.org/pdf/2505.09972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.9235000014305115,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2348322061","display_name":"Objective measurement of naturalistic interaction and early social networks","funder_award_id":"2150830","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/F4320315019","display_name":"Simons Foundation Autism Research Initiative","ror":"https://ror.org/01cmst727"},{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415399178.pdf","grobid_xml":"https://content.openalex.org/works/W4415399178.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1970017311","https://openalex.org/W1978313163","https://openalex.org/W1988577457","https://openalex.org/W2500128508","https://openalex.org/W2605959375","https://openalex.org/W2617454759","https://openalex.org/W2755308410","https://openalex.org/W2783786043","https://openalex.org/W2803334560","https://openalex.org/W2958687782","https://openalex.org/W3031133340","https://openalex.org/W3049615304","https://openalex.org/W3126731722","https://openalex.org/W3128683352","https://openalex.org/W3130231185","https://openalex.org/W3203749109","https://openalex.org/W3210037646","https://openalex.org/W4205246758","https://openalex.org/W4214857398","https://openalex.org/W4283367658","https://openalex.org/W4287855151","https://openalex.org/W4295152411","https://openalex.org/W4381611316","https://openalex.org/W4387762985","https://openalex.org/W4392100823","https://openalex.org/W4401907172"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,74,155],"automated":[4],"framework":[5,153],"(WSW":[6],"2.0)":[7],"for":[8,78,95,98,113,173],"analyzing":[9],"vocal":[10],"interactions":[11],"in":[12],"preschool":[13,202],"classrooms,":[14],"enhancing":[15],"both":[16],"accuracy":[17,71],"and":[18,27,30,47,73,123,132,136,161,185,211],"scalability":[19],"through":[20],"the":[21,152,170,180],"integration":[22],"of":[23,36,39,116,165,182,198,201],"wav2vec2-based":[24],"speaker":[25,79],"classification":[26,80],"Whisper":[28],"(large-v2":[29],"large-v3)":[31],"speech":[32],"transcription.":[33],"A":[34],"total":[35],"235":[37],"minutes":[38,43,49],"audio":[40,167],"recordings":[41],"(160":[42],"from":[44,50],"12":[45],"children":[46],"75":[48],"5":[51],"teachers),":[52],"were":[53],"used":[54],"to":[55,59,88,134,154,190],"compare":[56],"system":[57],"outputs":[58],"expert":[60,111],"human":[61],"annotations.":[62],"WSW":[63,100],"2.0":[64,101],"achieves":[65],"a":[66,114],"weighted":[67],"F1":[68],"score":[69],"of.845,":[70],"of.846,":[72],"error-corrected":[75],"kappa":[76],"of.672":[77],"(child":[81],"vs.":[82],"teacher).":[83],"Transcription":[84],"quality":[85],"is":[86],"moderate":[87],"high":[89,104],"with":[90,110],"word":[91],"error":[92],"rates":[93],"of.119":[94],"teachers":[96],"and.238":[97],"children.":[99],"exhibits":[102],"relatively":[103],"absolute":[105,141],"agreement":[106,142],"intraclass":[107,143],"correlations":[108,144],"(ICC)":[109],"transcriptions":[112],"range":[115],"classroom":[117,166,203],"language":[118,187,215],"features.":[119],"These":[120,177],"include":[121],"teacher":[122],"child":[124],"mean":[125],"utterance":[126],"length,":[127],"lexical":[128],"diversity,":[129],"question":[130],"asking,":[131],"responses":[133],"questions":[135],"other":[137],"utterances,":[138],"which":[139],"show":[140],"between.64":[145],"and.98.":[146],"To":[147],"establish":[148],"scalability,":[149],"we":[150],"apply":[151],"extensive":[156],"dataset":[157],"spanning":[158],"two":[159],"years":[160],"over":[162],"1,592":[163],"hours":[164],"recordings,":[168],"demonstrating":[169],"framework?s":[171],"robustness":[172],"broad":[174],"real-world":[175],"applications.":[176],"findings":[178],"highlight":[179],"potential":[181],"deep":[183],"learning":[184],"natural":[186],"processing":[188],"techniques":[189],"revolutionize":[191],"educational":[192],"research":[193],"by":[194],"providing":[195],"accurate":[196],"measures":[197],"key":[199],"features":[200],"speech,":[204],"ultimately":[205],"guiding":[206],"more":[207],"effective":[208],"intervention":[209],"strategies":[210],"supporting":[212],"early":[213],"childhood":[214],"development.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-10-22T00:00:00"}