{"id":"https://openalex.org/W2889624961","doi":"https://doi.org/10.1145/3242969.3243014","title":"Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition","display_name":"Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2889624961","doi":"https://doi.org/10.1145/3242969.3243014","mag":"2889624961"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3243014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3243014","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.01728","any_repository_has_fulltext":true},"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042852762","display_name":"Christian Saam","orcid":"https://orcid.org/0000-0002-6194-0835"},"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":false,"raw_author_name":"Christian Saam","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042231269","display_name":"Naomi Harte","orcid":"https://orcid.org/0000-0002-9274-209X"},"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":false,"raw_author_name":"Naomi Harte","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":3,"corresponding_author_ids":["https://openalex.org/A5034046565"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":5.966,"has_fulltext":true,"cited_by_count":74,"citation_normalized_percentile":{"value":0.97006962,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"115"},"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":0.9991000294685364,"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":0.9961000084877014,"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":0.817745566368103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7769330143928528},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7129355669021606},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7114449739456177},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.572795569896698},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.497266560792923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4889194071292877},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4792064130306244},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45592713356018066},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.44500964879989624},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4164380729198456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39683079719543457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817745566368103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7769330143928528},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7129355669021606},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7114449739456177},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.572795569896698},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.497266560792923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4889194071292877},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4792064130306244},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45592713356018066},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.44500964879989624},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4164380729198456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39683079719543457},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3242969.3243014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3243014","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"},{"id":"pmh:oai:arXiv.org:1809.01728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.01728","pdf_url":"https://arxiv.org/pdf/1809.01728","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:http://www.rian.ie/171181/","is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/89624","pdf_url":"http://hdl.handle.net/2262/89624","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sterpu, G., Saam, C., Harte, N. Attention-based audio-visual fusion for robust automatic speech recognition, ICMI\u201918, October 16-20, 2018, Boulder, CO, USA","raw_type":"Conference item"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.01728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.01728","pdf_url":"https://arxiv.org/pdf/1809.01728","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G228147372","display_name":null,"funder_award_id":"Grant 13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2563910032","display_name":null,"funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3993907298","display_name":null,"funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1518556865","https://openalex.org/W2029199293","https://openalex.org/W2096391593","https://openalex.org/W2116261113","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2184188583","https://openalex.org/W2302255633","https://openalex.org/W2395639500","https://openalex.org/W2403757143","https://openalex.org/W2519656895","https://openalex.org/W2560674852","https://openalex.org/W2594690981","https://openalex.org/W2619383789","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2785523195","https://openalex.org/W2787581402","https://openalex.org/W2790326622","https://openalex.org/W2952746495","https://openalex.org/W2953092061","https://openalex.org/W2962718314","https://openalex.org/W2962824709","https://openalex.org/W2963356069","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963710346","https://openalex.org/W2964308564","https://openalex.org/W3173163413","https://openalex.org/W4396952261"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,13,76],"recognition":[2,18,53],"can":[3,100,132],"potentially":[4],"benefit":[5],"from":[6,108],"the":[7,16,43,52,66,92,116,122,129],"lip":[8],"motion":[9],"patterns,":[10],"complementing":[11],"acoustic":[12,117,123],"to":[14,40,47,111,135],"improve":[15],"overall":[17],"performance,":[19],"particularly":[20],"in":[21,55],"noise.":[22],"In":[23],"this":[24],"paper":[25],"we":[26],"propose":[27],"an":[28],"audio-visual":[29],"fusion":[30,130],"strategy":[31,64,131],"that":[32,97,128],"goes":[33],"beyond":[34],"simple":[35],"feature":[36],"concatenation":[37],"and":[38,58,68],"learns":[39],"automatically":[41],"align":[42],"two":[44],"modalities,":[45],"leading":[46],"enhanced":[48],"representations":[49],"which":[50,140],"increase":[51],"accuracy":[54],"both":[56],"clean":[57],"noisy":[59],"conditions.":[60],"We":[61,87,126],"test":[62],"our":[63,98],"on":[65,113,121],"TCD-TIMIT":[67,114],"LRS2":[69],"datasets,":[70],"designed":[71],"for":[72],"large":[73],"vocabulary":[74],"continuous":[75],"recognition,":[77],"applying":[78],"three":[79],"types":[80],"of":[81,91],"noise":[82,124],"at":[83],"different":[84],"power":[85],"ratios.":[86],"also":[88],"exploit":[89],"state":[90],"art":[93],"Sequence-to-Sequence":[94],"architectures,":[95],"showing":[96],"method":[99],"be":[101],"easily":[102,133],"integrated.":[103],"Results":[104],"show":[105],"relative":[106],"improvements":[107],"7%":[109],"up":[110],"30%":[112],"over":[115],"modality":[118],"alone,":[119],"depending":[120],"level.":[125],"anticipate":[127],"generalise":[134],"many":[136],"other":[137],"multimodal":[138],"tasks":[139],"involve":[141],"correlated":[142],"modalities.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}