{"id":"https://openalex.org/W4416036243","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.814","title":"Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks","display_name":"Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036243","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.814"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.814","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.814","pdf_url":"https://aclanthology.org/2025.emnlp-main.814.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.814.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114988322","display_name":"Supriti Sinhamahapatra","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Supriti Sinhamahapatra","raw_affiliation_strings":["Karlsruhe Institute of Technology , Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology , Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039656339","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0003-4016-9129"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":["Karlsruhe Institute of Technology , Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology , Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114988322"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18420462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16111","last_page":"16121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.5634999871253967,"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/T12031","display_name":"Speech and dialogue systems","score":0.5634999871253967,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.061900001019239426,"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/T10028","display_name":"Topic Modeling","score":0.04919999837875366,"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/transcription","display_name":"Transcription (linguistics)","score":0.6607999801635742},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5152000188827515},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.22300000488758087},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2215999960899353}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6607999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5458999872207642},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24240000545978546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.22300000488758087},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2215999960899353},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.21860000491142273},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.21549999713897705}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.814","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.814","pdf_url":"https://aclanthology.org/2025.emnlp-main.814.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.814","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.814","pdf_url":"https://aclanthology.org/2025.emnlp-main.814.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036243.pdf","grobid_xml":"https://content.openalex.org/works/W4416036243.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"State-of-the-art":[0],"(SOTA)":[1],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"systems":[6],"primarily":[7],"rely":[8],"on":[9,28,39],"acoustic":[10],"information":[11,18],"while":[12],"disregarding":[13],"additional":[14],"multi-modal":[15,76],"context.However,":[16],"visual":[17],"are":[19],"essential":[20],"in":[21,102,106],"disambiguation":[22],"and":[23,116],"adaptation.While":[24],"most":[25],"work":[26,36],"focus":[27],"speaker":[29],"images":[30],"to":[31,122],"handle":[32],"noise":[33],"conditions,":[34],"this":[35],"also":[37],"focuses":[38],"integrating":[40],"presentation":[41,59],"slides":[42,85],"for":[43,57,71,118],"the":[44,79,98,123],"use":[45],"cases":[46],"of":[47,64,81,90,110],"scientific":[48],"presentation.In":[49],"a":[50,55,87,95,103],"first":[51],"step,":[52],"we":[53,68,93],"create":[54],"benchmark":[56],"multimodal":[58],"including":[60],"an":[61],"automatic":[62],"analysis":[63],"transcribing":[65],"domain-specific":[66],"terminology.Next,":[67],"explore":[69],"methods":[70],"augmenting":[72],"speech":[73],"models":[74],"with":[75,83],"information.We":[77],"mitigate":[78],"lack":[80],"datasets":[82],"accompanying":[84],"by":[86],"suitable":[88],"approach":[89],"data":[91],"augmentation.Finally,":[92],"train":[94],"model":[96],"using":[97],"augmented":[99],"dataset,":[100],"resulting":[101],"relative":[104],"reduction":[105],"word":[107],"error":[108],"rate":[109],"approximately":[111],"34%,":[112],"across":[113],"all":[114],"words":[115],"35%,":[117],"domainspecific":[119],"terms":[120],"compared":[121],"baseline":[124],"model.Our":[125],"implementation":[126],"is":[127],"available":[128],"1":[129],".":[130]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}
