{"id":"https://openalex.org/W4372260522","doi":"https://doi.org/10.1109/icassp49357.2023.10095555","title":"End-to-End Word-Level Disfluency Detection and Classification in Children\u2019s Reading Assessment","display_name":"End-to-End Word-Level Disfluency Detection and Classification in Children\u2019s Reading Assessment","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260522","doi":"https://doi.org/10.1109/icassp49357.2023.10095555"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030985243","display_name":"Lavanya Venkatasubramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lavanya Venkatasubramaniam","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145191","display_name":"Vishal Sunder","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal Sunder","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.9872000217437744,"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":0.9828000068664551,"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":0.8302956223487854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6420614719390869},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6344654560089111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5801490545272827},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5640034675598145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5026137828826904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4866984188556671},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46205297112464905},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4458162784576416},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1039419174194336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302956223487854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6420614719390869},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6344654560089111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5801490545272827},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5640034675598145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5026137828826904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4866984188556671},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46205297112464905},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4458162784576416},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1039419174194336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8999999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1855892484","https://openalex.org/W1979759871","https://openalex.org/W2039568842","https://openalex.org/W2747874407","https://openalex.org/W2795003080","https://openalex.org/W2911451850","https://openalex.org/W2972797781","https://openalex.org/W3008371301","https://openalex.org/W3097747488","https://openalex.org/W3161639065","https://openalex.org/W3197816268","https://openalex.org/W3207490364","https://openalex.org/W4214550505","https://openalex.org/W4224932945","https://openalex.org/W4225324745","https://openalex.org/W6639156005","https://openalex.org/W6946769850"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W1570025324","https://openalex.org/W2116902754","https://openalex.org/W376728115","https://openalex.org/W2166185180"],"abstract_inverted_index":{"Disfluency":[0],"detection":[1,40,126],"and":[2,41,52,121,130,132,138,145],"classification":[3,42,134],"on":[4,100,142],"children\u2019s":[5,18],"speech":[6,19],"has":[7],"a":[8,32,44,58,67,114,125,133],"great":[9],"potential":[10],"for":[11],"teaching":[12],"reading":[13,74],"skills.":[14],"Word-level":[15],"assessment":[16],"of":[17,69,128,136],"can":[20],"help":[21],"teachers":[22],"to":[23,36,54],"effectively":[24],"gauge":[25],"their":[26],"students\u2019":[27],"progress.":[28],"Hence,":[29],"we":[30,65,112],"propose":[31,113],"novel":[33,115],"attention-based":[34],"model":[35,90],"perform":[37],"word-level":[38,59],"disfluency":[39,60],"in":[43,82,109],"fully":[45],"end-to-end":[46],"(E2E)":[47],"manner":[48],"making":[49],"it":[50],"fast":[51],"easy":[53],"use.":[55],"We":[56,78],"develop":[57],"annotation":[61],"scheme":[62],"using":[63],"which":[64,96,123],"annotate":[66,80],"dataset":[68,76],"children":[70],"read":[71],"speech,":[72],"the":[73,83,106,110,143],"races":[75],"(READR).":[77],"also":[79],"disfluencies":[81],"existing":[84],"CMU":[85,146],"Kids":[86,147],"corpus.":[87],"The":[88],"proposed":[89],"significantly":[91],"outperforms":[92],"traditional":[93],"cascaded":[94],"baselines,":[95],"use":[97],"forced":[98],"alignments,":[99],"both":[101],"datasets.":[102],"To":[103],"deal":[104],"with":[105],"inevitable":[107],"class-imbalance":[108],"datasets,":[111],"technique":[116],"called":[117],"HiDeC":[118],"(Hierarchical":[119],"Detection":[120],"Classification)":[122],"yields":[124],"improvement":[127,135],"23%":[129],"16%":[131],"3.8%":[137],"19.3%":[139],"relative":[140],"F1-score":[141],"READR":[144],"datasets":[148],"respectively.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}