{"id":"https://openalex.org/W2894997731","doi":"https://doi.org/10.1145/3242969.3264976","title":"Large Vocabulary Continuous Audio-Visual Speech Recognition","display_name":"Large Vocabulary Continuous Audio-Visual Speech Recognition","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2894997731","doi":"https://doi.org/10.1145/3242969.3264976","mag":"2894997731"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3264976","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3264976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","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/A5034046565","display_name":"George Sterpu","orcid":"https://orcid.org/0000-0002-8724-9188"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"George Sterpu","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034046565"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10594709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9966999888420105,"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":0.7868390083312988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7127938270568848},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6547572016716003},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6280920505523682},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5461361408233643},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5329704284667969},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5115872025489807},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.49543845653533936},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4135666489601135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36611002683639526},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3513065278530121},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.33123064041137695},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2657317817211151},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1439906656742096},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10532137751579285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868390083312988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7127938270568848},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6547572016716003},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6280920505523682},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5461361408233643},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5329704284667969},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5115872025489807},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.49543845653533936},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4135666489601135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36611002683639526},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3513065278530121},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.33123064041137695},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2657317817211151},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1439906656742096},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10532137751579285},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3242969.3264976","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3264976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W2029199293","https://openalex.org/W2060510034","https://openalex.org/W2096391593","https://openalex.org/W2116261113","https://openalex.org/W2127141656","https://openalex.org/W2395639500","https://openalex.org/W2526425061","https://openalex.org/W2550980560","https://openalex.org/W2787944098","https://openalex.org/W2790326622","https://openalex.org/W2799525592","https://openalex.org/W2806872492","https://openalex.org/W2889624961","https://openalex.org/W2952746495","https://openalex.org/W2962824709","https://openalex.org/W2963894079","https://openalex.org/W2964308564","https://openalex.org/W3102469722","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2184127972","https://openalex.org/W1541790149","https://openalex.org/W3159882232","https://openalex.org/W2619911963","https://openalex.org/W2964829415","https://openalex.org/W4210930959","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"We":[0],"like":[1,48],"to":[2,27,49,61,96,106,113],"conversate":[3],"with":[4,39,80],"other":[5],"people":[6],"using":[7],"both":[8],"sounds":[9],"and":[10,32,60,103,117],"visuals,":[11],"as":[12],"our":[13],"perception":[14],"of":[15,56,64,83,99,111],"speech":[16,23,69,92],"is":[17],"bimodal.":[18],"Essentially":[19],"echoing":[20],"the":[21,29,35,40,53,75,81,100,108],"same":[22],"structure,":[24],"we":[25,46],"manage":[26],"integrate":[28,115],"two":[30],"modalities":[31],"often":[33],"understand":[34],"message":[36],"better":[37,67,114],"than":[38],"eyes":[41],"closed.":[42],"In":[43],"this":[44],"work":[45],"would":[47],"learn":[50],"more":[51],"about":[52],"visual":[54,116],"nature":[55],"speech,":[57],"coined":[58],"lip-reading,":[59],"make":[62],"use":[63],"it":[65],"towards":[66],"automatic":[68],"recognition":[70],"systems.":[71],"Recent":[72],"developments":[73],"in":[74],"Machine":[76],"Learning":[77],"area,":[78],"together":[79],"release":[82],"suitable":[84],"audio-visual":[85],"datasets":[86],"aimed":[87],"at":[88],"large":[89],"vocabulary":[90],"continuous":[91],"recognition,":[93],"have":[94],"led":[95],"a":[97],"renewal":[98],"lip-reading":[101],"topic,":[102],"allow":[104],"us":[105],"address":[107],"recurring":[109],"question":[110],"how":[112],"acoustic":[118],"speech.":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}