{"id":"https://openalex.org/W2901907199","doi":"https://doi.org/10.1109/icassp.2019.8683733","title":"Modality Attention for End-to-end Audio-visual Speech Recognition","display_name":"Modality Attention for End-to-end Audio-visual Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2901907199","doi":"https://doi.org/10.1109/icassp.2019.8683733","mag":"2901907199"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101604461","display_name":"Wenwen Yang","orcid":"https://orcid.org/0009-0000-6891-5168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenwen Yang","raw_affiliation_strings":["Voice Interaction Technology Center, Sogou Inc., Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voice Interaction Technology Center, Sogou Inc., Beijing, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344582","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-3720-718X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Voice Interaction Technology Center, Sogou Inc., Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voice Interaction Technology Center, Sogou Inc., Beijing, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645710","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-8623-1111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["Voice Interaction Technology Center, Sogou Inc., Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voice Interaction Technology Center, Sogou Inc., Beijing, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9852,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.98751592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6565","last_page":"6569"},"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":0.9986000061035156,"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/speech-recognition","display_name":"Speech recognition","score":0.8102271556854248},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7948599457740784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7871397733688354},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5982390642166138},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5549771785736084},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.46674472093582153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4598861634731293},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4485428035259247},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4248332679271698},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4233390688896179},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3633315861225128},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11518213152885437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06584301590919495}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8102271556854248},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7948599457740784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871397733688354},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5982390642166138},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5549771785736084},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.46674472093582153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4598861634731293},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4485428035259247},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4248332679271698},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4233390688896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3633315861225128},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11518213152885437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06584301590919495},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W1518556865","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W2015394094","https://openalex.org/W2076462394","https://openalex.org/W2096391593","https://openalex.org/W2102113734","https://openalex.org/W2115252128","https://openalex.org/W2120974626","https://openalex.org/W2125013164","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2135150557","https://openalex.org/W2143612262","https://openalex.org/W2152826865","https://openalex.org/W2267805933","https://openalex.org/W2327501763","https://openalex.org/W2550980560","https://openalex.org/W2551572271","https://openalex.org/W2556171197","https://openalex.org/W2594690981","https://openalex.org/W2603597171","https://openalex.org/W2746095516","https://openalex.org/W2889367162","https://openalex.org/W2889624961","https://openalex.org/W2952746495","https://openalex.org/W2962824709","https://openalex.org/W2963414781","https://openalex.org/W2963454111","https://openalex.org/W2963654155","https://openalex.org/W2964308564","https://openalex.org/W3102469722","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6729540071","https://openalex.org/W6729699919","https://openalex.org/W6734491695","https://openalex.org/W6739879593","https://openalex.org/W6746892368"],"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":{"Audio-visual":[0],"speech":[1,17,36],"recognition":[2,37,98],"(AVSR)":[3],"system":[4],"is":[5,54],"thought":[6],"to":[7,70,86,117],"be":[8,114],"one":[9],"of":[10],"the":[11,42,73,81,87],"most":[12],"promising":[13],"solutions":[14],"for":[15,34],"robust":[16],"recognition,":[18],"especially":[19],"in":[20],"noisy":[21,104],"environment.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"propose":[27],"a":[28],"novel":[29],"multimodal":[30,119],"attention":[31,109],"based":[32,48,110],"method":[33,53,112],"audio-visual":[35],"which":[38],"could":[39],"automatically":[40],"learn":[41],"fused":[43],"representation":[44],"from":[45,67],"both":[46,101],"modalities":[47],"on":[49,80],"their":[50],"importance.":[51],"Our":[52],"realized":[55],"using":[56],"state-of-the-art":[57],"sequence-to-sequence":[58],"(Seq2seq)":[59],"architectures.":[60],"Experimental":[61],"results":[62],"show":[63],"that":[64],"relative":[65],"improvements":[66],"2%":[68],"up":[69],"36%":[71],"over":[72],"auditory":[74],"modality":[75,108],"alone":[76],"are":[77],"obtained":[78],"depending":[79],"different":[82],"signal-to-noise-ratio":[83],"(SNR).":[84],"Compared":[85],"traditional":[88],"feature":[89],"concatenation":[90],"methods,":[91],"our":[92],"proposed":[93],"approach":[94],"can":[95,113],"achieve":[96],"better":[97],"performance":[99],"under":[100],"clean":[102],"and":[103],"conditions.":[105],"We":[106],"believe":[107],"end-to-end":[111],"easily":[115],"generalized":[116],"other":[118],"tasks":[120],"with":[121],"correlated":[122],"information.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}