{"id":"https://openalex.org/W4392903183","doi":"https://doi.org/10.1109/icassp48485.2024.10446486","title":"End-To-End Real Time Tracking of Children\u2019s Reading with Pointer Network","display_name":"End-To-End Real Time Tracking of Children\u2019s Reading with Pointer Network","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903183","doi":"https://doi.org/10.1109/icassp48485.2024.10446486"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446486","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":"middle","author":{"id":"https://openalex.org/A5093096687","display_name":"Beulah Karrolla","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":"Beulah Karrolla","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11731","last_page":"11735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8311436176300049},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.7775173187255859},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6854403614997864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621513307094574},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.5256427526473999},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5173556208610535},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45662155747413635},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4499283730983734},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4444505572319031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4268135726451874},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4100732207298279},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.34498006105422974},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.19757050275802612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311436176300049},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.7775173187255859},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6854403614997864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621513307094574},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.5256427526473999},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5173556208610535},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45662155747413635},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4499283730983734},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4444505572319031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268135726451874},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4100732207298279},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.34498006105422974},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.19757050275802612},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446486","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W343483379","https://openalex.org/W1494198834","https://openalex.org/W1506069822","https://openalex.org/W1821462560","https://openalex.org/W2013196554","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2366124425","https://openalex.org/W2747874407","https://openalex.org/W2911451850","https://openalex.org/W3008371301","https://openalex.org/W3043783436","https://openalex.org/W3127686677","https://openalex.org/W3197816268","https://openalex.org/W3200938764","https://openalex.org/W4320013820","https://openalex.org/W4372260522","https://openalex.org/W6638523607","https://openalex.org/W6677994422","https://openalex.org/W6712141947","https://openalex.org/W6725207838","https://openalex.org/W6946769850"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W2151749779","https://openalex.org/W1573546415","https://openalex.org/W3179968364","https://openalex.org/W2906993205","https://openalex.org/W2071572975","https://openalex.org/W2619993508","https://openalex.org/W2808291730","https://openalex.org/W2963789888"],"abstract_inverted_index":{"In":[0],"this":[1,66],"work,":[2],"we":[3,28,69,97],"explore":[4],"how":[5],"a":[6,30,45,99,120,175],"real":[7],"time":[8],"reading":[9,21],"tracker":[10],"can":[11,151],"be":[12],"built":[13],"efficiently":[14],"for":[15,124],"children\u2019s":[16,140,165],"voices.":[17],"While":[18],"previously":[19],"proposed":[20],"trackers":[22],"focused":[23],"on":[24,60,88,132,170,178],"ASR-based":[25],"cascaded":[26],"approaches,":[27],"propose":[29],"fully":[31],"end-to-end":[32],"model":[33,103,150],"making":[34],"it":[35],"less":[36],"prone":[37],"to":[38,51,112],"lags":[39],"in":[40,54,109],"voice":[41],"tracking.":[42],"We":[43],"employ":[44],"pointer":[46,67,126],"network":[47],"that":[48],"directly":[49],"learns":[50],"predict":[52],"positions":[53],"the":[55,61,80,84,89,113,125,160,179],"ground":[56,71],"truth":[57,72],"text":[58,85],"conditioned":[59],"streaming":[62],"speech.":[63],"To":[64],"train":[65],"network,":[68],"generate":[70],"training":[73,90,122],"signals":[74],"by":[75],"using":[76],"forced":[77,94],"alignment":[78,95,110],"between":[79],"read":[81,87],"speech":[82,135,141,155,166],"and":[83,138,145,159,163,174],"being":[86],"set.":[91],"Exploring":[92],"different":[93],"models,":[96],"find":[98],"neural":[100],"attention":[101],"based":[102],"is":[104,119],"at":[105],"least":[106],"as":[107],"close":[108],"accuracy":[111,158,169,177],"Montreal":[114],"Forced":[115],"Aligner,":[116],"but":[117],"surprisingly":[118],"better":[121],"signal":[123],"network.":[127],"Our":[128,148],"results":[129],"are":[130],"reported":[131],"one":[133],"adult":[134,154],"data":[136,173],"(TIMIT)":[137],"two":[139],"datasets":[142],"(CMU":[143],"Kids":[144,172],"Reading":[146,180],"Races).":[147],"best":[149],"accurately":[152],"track":[153],"with":[156,167],"87.8%":[157],"much":[161],"harder":[162],"disfluent":[164],"77.1%":[168],"CMU":[171],"65.3%":[176],"Races":[181],"dataset.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}