{"id":"https://openalex.org/W3148906368","doi":"https://doi.org/10.1109/slt48900.2021.9383466","title":"Listen, Look and Deliberate: Visual Context-Aware Speech Recognition Using Pre-Trained Text-Video Representations","display_name":"Listen, Look and Deliberate: Visual Context-Aware Speech Recognition Using Pre-Trained Text-Video Representations","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3148906368","doi":"https://doi.org/10.1109/slt48900.2021.9383466","mag":"3148906368"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5075220607","display_name":"Shahram Ghorbani","orcid":"https://orcid.org/0000-0002-8118-5515"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahram Ghorbani","raw_affiliation_strings":["Microsoft Speech and Language Group","The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597408","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1872-3429"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"628"},"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8555830717086792},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7121397256851196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7056891918182373},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5477300882339478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47935038805007935},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4651291072368622},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3329859972000122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3212065100669861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555830717086792},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7121397256851196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7056891918182373},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5477300882339478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47935038805007935},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4651291072368622},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3329859972000122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3212065100669861},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W2133564696","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2512544816","https://openalex.org/W2578229578","https://openalex.org/W2714726990","https://openalex.org/W2752047430","https://openalex.org/W2810643877","https://openalex.org/W2889903020","https://openalex.org/W2890952074","https://openalex.org/W2899274165","https://openalex.org/W2903320905","https://openalex.org/W2914781455","https://openalex.org/W2938973646","https://openalex.org/W2950133079","https://openalex.org/W2953472911","https://openalex.org/W2962866381","https://openalex.org/W2962934715","https://openalex.org/W2963250244","https://openalex.org/W2963360627","https://openalex.org/W2963902314","https://openalex.org/W2964121744","https://openalex.org/W2964182350","https://openalex.org/W2964308564","https://openalex.org/W2973122799","https://openalex.org/W3011339933","https://openalex.org/W3015678833","https://openalex.org/W3023282145","https://openalex.org/W3035635319","https://openalex.org/W3105232955","https://openalex.org/W4288297863","https://openalex.org/W4298112588","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6679434410","https://openalex.org/W6732872814","https://openalex.org/W6743726175","https://openalex.org/W6754392867","https://openalex.org/W6755559483","https://openalex.org/W6756706075","https://openalex.org/W6764984290"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2890132085","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W4392903592"],"abstract_inverted_index":{"In":[0],"this":[1,82],"study,":[2],"we":[3,46,94,208],"try":[4],"to":[5,13,31,52,111,160,166,242],"address":[6],"the":[7,68,90,98,126,162,168,171,189,194,215,221,235,252],"problem":[8],"of":[9,64,151,230],"leveraging":[10],"visual":[11,22,99,135,140,172],"signals":[12,54],"improve":[14],"Automatic":[15],"Speech":[16],"Recognition":[17],"(ASR),":[18],"also":[19,95,108,157,249],"known":[20],"as":[21,112],"context-aware":[23,141],"ASR":[24,129,155],"(VC-ASR).":[25],"We":[26,79,192],"explore":[27,96],"novel":[28],"VC-ASR":[29,190],"approaches":[30],"leverage":[32,53,161],"video":[33,59],"and":[34,58,71,122,130,156,182,203,224,232,237],"text":[35,123,164],"representations":[36,121],"extracted":[37],"by":[38,255],"a":[39,48,72,102,113,134,226],"self-supervised":[40],"pre-trained":[41,163],"text-video":[42],"embedding":[43],"model.":[44,245],"Firstly,":[45],"propose":[47],"multi-stream":[49,181,222],"attention":[50],"architecture":[51,62,83],"from":[55,125],"both":[56],"audio":[57,120,201,205],"modalities.":[60],"This":[61],"consists":[63],"separate":[65],"encoders":[66],"for":[67,137,197,234],"two":[69,198],"modalities":[70,88],"single":[73],"decoder":[74],"that":[75,81,180],"at-tends":[76],"over":[77],"them.":[78],"show":[80,179],"is":[84],"better":[85],"than":[86],"fusing":[87],"at":[89,188],"signal":[91],"level.":[92],"Additionally,":[93],"lever-aging":[97],"information":[100],"in":[101,206,214],"second":[103],"pass":[104,128],"model,":[105],"which":[106,207],"has":[107],"been":[109],"referred":[110],"`deliberation":[114],"model'.":[115],"The":[116,143,217,246],"deliberation":[117,145,183,218,247],"model":[118,165,219,223,248],"accepts":[119],"hypotheses":[124,169],"first":[127],"combines":[131],"them":[132],"with":[133,170],"stream":[136,202],"an":[138,243],"improved":[139],"recognition.":[142],"proposed":[144,195],"scheme":[146],"can":[147],"work":[148],"on":[149,176],"top":[150],"any":[152],"well":[153],"trained":[154],"enabled":[158],"us":[159],"ground":[167],"features.":[173],"Our":[174],"experiments":[175],"HOW2":[177],"dataset":[178],"architectures":[184],"are":[185],"very":[186],"effective":[187],"task.":[191],"evaluate":[193],"models":[196],"scenarios;":[199],"clean":[200,236],"distorted":[204],"mask":[209],"out":[210],"some":[211],"specific":[212],"words":[213,254],"audio.":[216],"outperforms":[220],"achieves":[225],"relative":[227],"WER":[228],"improvement":[229],"6%":[231],"8.7%":[233],"masked":[238,253],"data,":[239],"respectively,":[240],"compared":[241],"audio-only":[244],"improves":[250],"re-covering":[251],"59%":[256],"relative.":[257]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}