{"id":"https://openalex.org/W2798400235","doi":"https://doi.org/10.1109/icassp.2018.8462439","title":"End-to-end Multimodal Speech Recognition","display_name":"End-to-end Multimodal Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2798400235","doi":"https://doi.org/10.1109/icassp.2018.8462439","mag":"2798400235"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.09713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036933477","display_name":"Shruti Palaskar","orcid":"https://orcid.org/0000-0001-8637-1897"},"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":"Shruti Palaskar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A","Carnegie Mellon University,Pittsburgh,PA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053704856","display_name":"Ramon Sanabria","orcid":null},"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":"Ramon Sanabria","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A","Carnegie Mellon University,Pittsburgh,PA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A","Carnegie Mellon University,Pittsburgh,PA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8314,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72762823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5774","last_page":"5778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9995999932289124,"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/T10860","display_name":"Speech 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8027431964874268},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7582888603210449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6424160003662109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49549996852874756},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4931408762931824},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46203142404556274},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4421749413013458},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30164745450019836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027431964874268},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7582888603210449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6424160003662109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49549996852874756},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4931408762931824},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46203142404556274},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4421749413013458},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30164745450019836},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.09713","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.09713","pdf_url":"https://arxiv.org/pdf/1804.09713","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":"","raw_type":null},{"id":"mag:2798400235","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.09713.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.09713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.09713","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.09713","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.09713","pdf_url":"https://arxiv.org/pdf/1804.09713","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":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G6524269621","display_name":null,"funder_award_id":"OCI-1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6778350887","display_name":null,"funder_award_id":"1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798400235.pdf","grobid_xml":"https://content.openalex.org/works/W2798400235.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1533416326","https://openalex.org/W1586532344","https://openalex.org/W1710082047","https://openalex.org/W1736701665","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1929897159","https://openalex.org/W1985371235","https://openalex.org/W2015633636","https://openalex.org/W2033256038","https://openalex.org/W2045317385","https://openalex.org/W2048526313","https://openalex.org/W2079623482","https://openalex.org/W2102113734","https://openalex.org/W2113786253","https://openalex.org/W2117671523","https://openalex.org/W2121486117","https://openalex.org/W2127141656","https://openalex.org/W2132339004","https://openalex.org/W2134670479","https://openalex.org/W2151096985","https://openalex.org/W2296073425","https://openalex.org/W2398776621","https://openalex.org/W2402146185","https://openalex.org/W2406753715","https://openalex.org/W2512544816","https://openalex.org/W2526425061","https://openalex.org/W2745596852","https://openalex.org/W2769180089","https://openalex.org/W2949888546","https://openalex.org/W2950903920","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963537349","https://openalex.org/W6640280077","https://openalex.org/W6646979388","https://openalex.org/W6654250109","https://openalex.org/W6675365184","https://openalex.org/W6679436768","https://openalex.org/W6679792166","https://openalex.org/W6680532216","https://openalex.org/W6684191040","https://openalex.org/W6712930963","https://openalex.org/W6713877832","https://openalex.org/W6725564660","https://openalex.org/W6732580896","https://openalex.org/W6739955027","https://openalex.org/W6746177234"],"related_works":["https://openalex.org/W2962866381","https://openalex.org/W2912668608","https://openalex.org/W2963946371","https://openalex.org/W2912937645","https://openalex.org/W3014677573","https://openalex.org/W2914781455","https://openalex.org/W2940073716","https://openalex.org/W2913851961","https://openalex.org/W3039958863","https://openalex.org/W2062652351","https://openalex.org/W3091088345","https://openalex.org/W3017862536","https://openalex.org/W3108216882","https://openalex.org/W3211053973","https://openalex.org/W3206548307","https://openalex.org/W2995732811","https://openalex.org/W2883449998","https://openalex.org/W2293596383","https://openalex.org/W658444389","https://openalex.org/W3016042119"],"abstract_inverted_index":{"Transcription":[0],"or":[1],"sub-titling":[2],"of":[3,30,62,78,89,115,144],"open-domain":[4],"videos":[5],"is":[6],"still":[7],"a":[8,63,79,95,106],"challenging":[9,20],"domain":[10,29],"for":[11,94],"Automatic":[12],"Speech":[13],"Recognition":[14],"(ASR)":[15],"due":[16],"to":[17,52,72,129],"the":[18,26,31,40,54,76,87,113,132,142],"data's":[19],"acoustics,":[21],"variable":[22],"signal":[23],"processing":[24],"and":[25,46,58,65,91,117,126],"essentially":[27],"unrestricted":[28],"data.":[32],"In":[33,75],"previous":[34],"work,":[35],"we":[36,66,85],"have":[37],"shown":[38],"that":[39],"visual":[41],"channel":[42],"-":[43,49],"specifically":[44],"object":[45],"scene":[47],"features":[48],"can":[50],"help":[51],"adapt":[53],"acoustic":[55],"model":[56,60],"(AM)":[57],"language":[59],"(LM)":[61],"recognizer,":[64],"are":[67,102],"now":[68],"expanding":[69],"this":[70],"work":[71],"end-to-end":[73],"approaches.":[74,146],"case":[77],"Connectionist":[80],"Temporal":[81],"Classification":[82],"(CTC)-based":[83],"approach,":[84,98],"retain":[86],"separation":[88],"AM":[90],"LM,":[92],"while":[93],"sequence-to-sequence":[96],"(S2S)":[97],"both":[99,145],"information":[100],"sources":[101],"adapted":[103],"together,":[104],"in":[105],"single":[107],"model.":[108],"This":[109],"paper":[110],"also":[111],"analyzes":[112],"behavior":[114],"CTC":[116],"S2S":[118],"models":[119],"on":[120,131],"noisy":[121],"video":[122],"data":[123],"(How-To":[124],"corpus),":[125],"compares":[127],"it":[128],"results":[130],"clean":[133],"Wall":[134],"Street":[135],"Journal":[136],"(WSJ)":[137],"corpus,":[138],"providing":[139],"insight":[140],"into":[141],"robustness":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
