{"id":"https://openalex.org/W4323521120","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10052073","title":"Cross-utterance context for multimodal video transcription","display_name":"Cross-utterance context for multimodal video transcription","publication_year":2022,"publication_date":"2022-10-31","ids":{"openalex":"https://openalex.org/W4323521120","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10052073"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf56349.2022.10052073","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ieeeconf56349.2022.10052073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","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/A5056041031","display_name":"Roshan Sharma","orcid":"https://orcid.org/0000-0001-9886-009X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roshan Sharma","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,USA","Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University and Mohamed bin Zayed University of Artificial Intelligence Pittsburgh, USA and Masdar,Abu Dhabi,UAE","Carnegie Mellon University and Mohamed bin Zayed University of Artificial Intelligence Pittsburgh, USA and Masdar, Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University and Mohamed bin Zayed University of Artificial Intelligence Pittsburgh, USA and Masdar,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Carnegie Mellon University and Mohamed bin Zayed University of Artificial Intelligence Pittsburgh, USA and Masdar, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs/2010.11929","issue":null,"first_page":"1321","last_page":"1325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.8237043023109436},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8217901587486267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7905415296554565},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6792646646499634},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.44177037477493286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3864400386810303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3782792091369629},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3648080825805664},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12283748388290405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09488853812217712}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.8237043023109436},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8217901587486267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905415296554565},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6792646646499634},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.44177037477493286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3864400386810303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3782792091369629},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3648080825805664},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12283748388290405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09488853812217712},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf56349.2022.10052073","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ieeeconf56349.2022.10052073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2251849926","https://openalex.org/W2526425061","https://openalex.org/W2549139847","https://openalex.org/W2573537087","https://openalex.org/W2586850765","https://openalex.org/W2619947201","https://openalex.org/W2714726990","https://openalex.org/W2736272491","https://openalex.org/W2899274165","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962866381","https://openalex.org/W2963155035","https://openalex.org/W2963407669","https://openalex.org/W2964182350","https://openalex.org/W3007776460","https://openalex.org/W3035299099","https://openalex.org/W3096798607","https://openalex.org/W3133595249","https://openalex.org/W3148906368","https://openalex.org/W3163463193","https://openalex.org/W3197898596","https://openalex.org/W4225166170","https://openalex.org/W4285704072","https://openalex.org/W6691634444","https://openalex.org/W6729342207","https://openalex.org/W6736780767","https://openalex.org/W6741215079","https://openalex.org/W6755559483","https://openalex.org/W6802742088"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W3111427900","https://openalex.org/W4302009627","https://openalex.org/W4212781403","https://openalex.org/W4388989680","https://openalex.org/W2529301793","https://openalex.org/W4307784074","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"In":[0,43],"multimodal":[1,29,49,67],"speech":[2,50,116],"transcription":[3,17],"of":[4,14,100],"videos,":[5],"audio":[6],"and":[7,16,39,66,102],"video":[8,27,41],"are":[9],"segmented":[10],"using":[11,57],"the":[12,58,93,98],"concept":[13],"utterances,":[15],"is":[18],"performed":[19],"independently":[20],"on":[21,53,87,92],"these":[22],"segments.":[23],"However,":[24],"for":[25],"real-world":[26],"transcription,":[28],"information":[30,73],"from":[31],"past":[32,83],"utterances":[33],"can":[34],"be":[35],"leveraged":[36],"to":[37,70,81],"contextualize":[38],"improve":[40],"transcription.":[42],"this":[44],"work,":[45],"we":[46,78],"first":[47],"build":[48],"recognition":[51],"systems":[52],"instructional":[54],"YouTube":[55],"videos":[56],"How2":[59],"corpus.":[60],"We":[61],"examine":[62],"different":[63],"visual":[64,72],"representations":[65],"fusion":[68],"techniques":[69],"infuse":[71],"into":[74],"audio-only":[75,115],"models.":[76],"Then":[77],"explore":[79],"methods":[80],"embed":[82],"context":[84],"by":[85],"training":[86],"longer":[88],"input":[89],"sequences.":[90],"Experiments":[91],"How2-":[94],"300h":[95],"data":[96],"demonstrate":[97],"importance":[99],"multi-modality":[101],"long-term":[103],"context,":[104],"which":[105],"result":[106],"in":[107],"a":[108],"1":[109],"%":[110],"WER":[111],"absolute":[112],"improvement":[113],"over":[114],"recognizers.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}