{"id":"https://openalex.org/W3088950396","doi":"https://doi.org/10.1109/access.2020.3024218","title":"WaveNet With Cross-Attention for Audiovisual Speech Recognition","display_name":"WaveNet With Cross-Attention for Audiovisual Speech Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3088950396","doi":"https://doi.org/10.1109/access.2020.3024218","mag":"3088950396"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3024218","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3024218","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09197622.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09197622.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100460841","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8476-888X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8476-888X","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108724547","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0001-7831-5721"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7831-5721","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062078743","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0002-4007-7016"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4007-7016","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073134755","display_name":"Licheng Wu","orcid":"https://orcid.org/0000-0001-5739-634X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Wu","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.0129,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75983503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"169160","last_page":"169168"},"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":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8283324241638184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8246769905090332},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7327260971069336},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6878665685653687},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.661588191986084},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5316163897514343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5241268277168274},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.46036067605018616},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4501754939556122},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.33849066495895386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3321496248245239},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31781381368637085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06793519854545593}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8283324241638184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246769905090332},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7327260971069336},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6878665685653687},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.661588191986084},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5316163897514343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241268277168274},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.46036067605018616},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4501754939556122},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.33849066495895386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3321496248245239},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31781381368637085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06793519854545593},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3024218","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3024218","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09197622.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:52da65afa40f43e38cbce50c44f7d191","is_oa":true,"landing_page_url":"https://doaj.org/article/52da65afa40f43e38cbce50c44f7d191","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 169160-169168 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3024218","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3024218","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09197622.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1474490597","display_name":null,"funder_award_id":"111 Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1660390292","display_name":null,"funder_award_id":"61976236","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3088950396.pdf","grobid_xml":"https://content.openalex.org/works/W3088950396.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2029199293","https://openalex.org/W2102113734","https://openalex.org/W2120974626","https://openalex.org/W2125013164","https://openalex.org/W2133564696","https://openalex.org/W2135150557","https://openalex.org/W2144499799","https://openalex.org/W2152826865","https://openalex.org/W2404704342","https://openalex.org/W2519091744","https://openalex.org/W2545177271","https://openalex.org/W2551572271","https://openalex.org/W2746799361","https://openalex.org/W2790326622","https://openalex.org/W2889367162","https://openalex.org/W2889624961","https://openalex.org/W2901907199","https://openalex.org/W2916979304","https://openalex.org/W2953318193","https://openalex.org/W2962866381","https://openalex.org/W2963295405","https://openalex.org/W2963654155","https://openalex.org/W2963920996","https://openalex.org/W2964309797","https://openalex.org/W2970105555","https://openalex.org/W3007589762","https://openalex.org/W3102469722","https://openalex.org/W6629052376","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6726720044","https://openalex.org/W6728910023","https://openalex.org/W6756352736"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W4241778367","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"In":[0],"this":[1,40],"paper,":[2,41],"the":[3,50,70,77,86,92,107,127],"WaveNet":[4,28,59,87],"with":[5,88],"cross-attention":[6,51,65,89],"is":[7,29,53],"proposed":[8,64],"for":[9,32,60,132],"Audio-Visual":[10],"Automatic":[11],"Speech":[12],"Recognition":[13],"(AV-ASR)":[14],"to":[15,45,68,76,106,126],"address":[16],"multimodal":[17],"feature":[18,61,75,79,129],"fusion":[19],"and":[20,35,49,99,111,119],"frame":[21],"alignment":[22],"problems":[23],"between":[24],"two":[25],"data":[26],"streams.":[27],"usually":[30],"used":[31],"speech":[33,36,47,109],"generation":[34],"recognition,":[37,48,110],"however,":[38],"in":[39],"we":[42],"extent":[43],"it":[44],"audiovisual":[46],"mechanism":[52,66],"introduced":[54],"into":[55],"different":[56],"places":[57],"of":[58,73],"fusion.":[62],"The":[63,81],"tries":[67],"explore":[69],"correlated":[71],"frames":[72],"visual":[74],"acoustic":[78],"frame.":[80],"experimental":[82],"results":[83],"show":[84],"that":[85],"can":[90],"reduce":[91,112],"Tibetan":[93,113],"single":[94,114],"syllable":[95,115],"error":[96,102,116,122],"about":[97,103,117,123],"4.5%":[98],"English":[100,120],"word":[101,121],"39.8%":[104],"relative":[105,125],"audio-only":[108],"35.1%":[118],"21.6%":[124],"conventional":[128],"concatenation":[130],"method":[131],"AV-ASR.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
