{"id":"https://openalex.org/W4366762594","doi":"https://doi.org/10.1145/3587281.3587290","title":"Modeling Word Importance in Conversational Transcripts: Toward improved live captioning for Deaf and hard of hearing viewers","display_name":"Modeling Word Importance in Conversational Transcripts: Toward improved live captioning for Deaf and hard of hearing viewers","publication_year":2023,"publication_date":"2023-04-22","ids":{"openalex":"https://openalex.org/W4366762594","doi":"https://doi.org/10.1145/3587281.3587290","pmid":"https://pubmed.ncbi.nlm.nih.gov/41395353"},"language":"en","primary_location":{"id":"doi:10.1145/3587281.3587290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3587281.3587290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Web for All Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12697923/pdf/nihms-1917505.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021437143","display_name":"Akhter Al Amin","orcid":"https://orcid.org/0000-0003-0072-743X"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akhter Al Amin","raw_affiliation_strings":["Computing and Information Sciences, Rochester Institute of Technology, USA"],"raw_orcid":"https://orcid.org/0000-0003-0072-743X","affiliations":[{"raw_affiliation_string":"Computing and Information Sciences, Rochester Institute of Technology, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071804261","display_name":"Saad Hassan","orcid":"https://orcid.org/0000-0003-2792-2964"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saad Hassan","raw_affiliation_strings":["Computing and Information Sciences, Rochester Institute of Technology, USA"],"raw_orcid":"https://orcid.org/0000-0003-2792-2964","affiliations":[{"raw_affiliation_string":"Computing and Information Sciences, Rochester Institute of Technology, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034572826","display_name":"Matt Huenerfauth","orcid":"https://orcid.org/0000-0001-6290-2681"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Huenerfauth","raw_affiliation_strings":["School of Information, Rochester Institute of Technology, USA"],"raw_orcid":"https://orcid.org/0000-0001-6290-2681","affiliations":[{"raw_affiliation_string":"School of Information, Rochester Institute of Technology, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067170834","display_name":"Cecilia Ovesdotter Alm","orcid":"https://orcid.org/0000-0002-8730-0916"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cecilia Ovesdotter Alm","raw_affiliation_strings":["Department of Psychology, Rochester Institute of Technology, USA"],"raw_orcid":"https://orcid.org/0000-0002-8730-0916","affiliations":[{"raw_affiliation_string":"Department of Psychology, Rochester Institute of Technology, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7326,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67762303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2023","issue":null,"first_page":"79","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.851165771484375},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7435284852981567},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6504403352737427},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6458284854888916},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6176955103874207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5784981846809387},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5569990277290344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029181838035583},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4337605834007263},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4161291718482971},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.41008660197257996},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09667500853538513},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.08185890316963196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.851165771484375},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7435284852981567},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6504403352737427},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6458284854888916},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6176955103874207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5784981846809387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5569990277290344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029181838035583},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4337605834007263},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4161291718482971},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.41008660197257996},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09667500853538513},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.08185890316963196},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3587281.3587290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3587281.3587290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Web for All Conference","raw_type":"proceedings-article"},{"id":"pmid:41395353","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41395353","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"... International web for all conference. Web for All Conference","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12697923","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12697923/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12697923/pdf/nihms-1917505.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Int Web All Conf","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12697923","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12697923/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12697923/pdf/nihms-1917505.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Int Web All Conf","raw_type":"Text"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3468262003","display_name":"CHS: Medium: Critical Factors for Automatic Speech Recognition in Supporting Small Group Communication Between People who are Deaf or Hard of Hearing and Hearing Colleagues","funder_award_id":"1954284","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4624981801","display_name":"Collaborative Research: HCC: Medium: Linguistically-Driven Sign Recognition from Continuous Signing for American Sign Language (ASL)","funder_award_id":"2212303","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6769340260","display_name":"NRT-AI: AWARE-AI: AWAREness for Sensing Humans Responsibly with AI","funder_award_id":"2125362","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8356003408","display_name":null,"funder_award_id":"DGE-2125362","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/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366762594.pdf","grobid_xml":"https://content.openalex.org/works/W4366762594.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2133286915","https://openalex.org/W2143017621","https://openalex.org/W2250710312","https://openalex.org/W2798685342","https://openalex.org/W2952698673","https://openalex.org/W2963469172","https://openalex.org/W2973226110","https://openalex.org/W2981822980","https://openalex.org/W3023238803","https://openalex.org/W3153904578","https://openalex.org/W3165614589","https://openalex.org/W3200871535","https://openalex.org/W3207408393","https://openalex.org/W3213754079","https://openalex.org/W4206828928","https://openalex.org/W4229879597","https://openalex.org/W4283658620","https://openalex.org/W4391156274","https://openalex.org/W6931636349"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3200784702"],"abstract_inverted_index":{"Despite":[0],"the":[1,19,44,92,99,117,139],"recent":[2],"improvements":[3],"in":[4,14,24,63],"automatic":[5],"speech":[6],"recognition":[7],"(ASR)":[8],"systems,":[9],"their":[10],"accuracy":[11],"is":[12],"imperfect":[13],"live":[15,146],"conversational":[16,64],"settings.":[17],"Classifying":[18],"importance":[20,62,73,118],"of":[21,38,43,119,141],"each":[22],"word":[23,52,61,72],"a":[25,70,77,142],"caption":[26,45,147],"transcription":[27],"can":[28,137],"enable":[29],"evaluation":[30],"metrics":[31],"that":[32],"best":[33,122],"reflect":[34],"Deaf":[35],"and":[36,84,97],"Hard":[37],"Hearing":[39],"(DHH)":[40],"readers'":[41],"judgment":[42],"quality.":[46],"Prior":[47],"work":[48,67],"has":[49],"proposed":[50],"using":[51,107],"embeddings,":[53,58],"e.g.,":[54],"word2vec":[55],"or":[56],"BERT":[57],"to":[59],"model":[60,124],"transcripts.":[65],"Recent":[66],"also":[68],"disseminated":[69],"human-annotated":[71],"dataset.":[74],"We":[75,89],"conducted":[76],"word-token":[78],"level":[79],"analysis":[80],"on":[81,126],"this":[82],"dataset":[83,93,129],"explored":[85],"Part-of-Speech":[86],"(POS)":[87],"distribution.":[88],"then":[90],"augmented":[91,128],"with":[94],"POS":[95],"tags":[96],"reduced":[98],"class":[100],"imbalance":[101],"by":[102],"generating":[103],"5%":[104],"additional":[105],"text":[106],"masking.":[108],"Finally,":[109],"we":[110],"investigated":[111],"how":[112],"various":[113],"supervised":[114],"models":[115],"learn":[116],"words.":[120],"The":[121],"performing":[123],"trained":[125],"our":[127],"performed":[130],"better":[131],"than":[132],"prior":[133],"models.":[134],"Our":[135],"findings":[136],"inform":[138],"design":[140],"metric":[143],"for":[144],"measuring":[145],"quality":[148],"from":[149],"DHH":[150],"users'":[151],"perspectives.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2023-04-24T00:00:00"}