{"id":"https://openalex.org/W2980600748","doi":"https://doi.org/10.1145/3340555.3356102","title":"Deep Audio-visual System for Closed-set Word-level Speech Recognition","display_name":"Deep Audio-visual System for Closed-set Word-level Speech Recognition","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980600748","doi":"https://doi.org/10.1145/3340555.3356102","mag":"2980600748"},"language":"en","primary_location":{"id":"doi:10.1145/3340555.3356102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3356102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5017808406","display_name":"Yougen Yuan","orcid":"https://orcid.org/0000-0002-2490-566X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yougen Yuan","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057130910","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0002-4431-3506"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tang","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028107736","display_name":"Minhao Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minhao Fan","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006794082","display_name":"Yue Cao","orcid":"https://orcid.org/0000-0002-2098-7637"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Cao","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364068","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9690-7026"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017808406"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.1659,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45685528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"540","last_page":"545"},"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":0.9987999796867371,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8442873954772949},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7903627157211304},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5685423612594604},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5206957459449768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4975323975086212},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.49551236629486084},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.47554418444633484},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.47067293524742126},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.35725343227386475},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35156387090682983},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11402589082717896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8442873954772949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7903627157211304},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5685423612594604},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5206957459449768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975323975086212},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.49551236629486084},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.47554418444633484},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.47067293524742126},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.35725343227386475},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35156387090682983},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11402589082717896},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340555.3356102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3356102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1745048755","display_name":null,"funder_award_id":"2018JM6015","funder_id":"https://openalex.org/F4320335467","funder_display_name":"Natural Science Foundation of Shaanxi Provincial Department of Education"},{"id":"https://openalex.org/G412693967","display_name":null,"funder_award_id":"61571363,61571362","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G514700904","display_name":null,"funder_award_id":"3102019ZY1004","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320335467","display_name":"Natural Science Foundation of Shaanxi Provincial Department of Education","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1522734439","https://openalex.org/W2022799064","https://openalex.org/W2076462394","https://openalex.org/W2096391593","https://openalex.org/W2102113734","https://openalex.org/W2121486117","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2261706002","https://openalex.org/W2293634267","https://openalex.org/W2398406965","https://openalex.org/W2406846463","https://openalex.org/W2511073133","https://openalex.org/W2556171197","https://openalex.org/W2579335913","https://openalex.org/W2596627958","https://openalex.org/W2890952074","https://openalex.org/W2899771611","https://openalex.org/W2944964836","https://openalex.org/W2963192365","https://openalex.org/W2963356069","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2121486117","https://openalex.org/W4300529166","https://openalex.org/W3196861523","https://openalex.org/W2403424637","https://openalex.org/W4287824696","https://openalex.org/W99318944","https://openalex.org/W3012645992","https://openalex.org/W4285483475","https://openalex.org/W14943941","https://openalex.org/W4206612152"],"abstract_inverted_index":{"Audio-visual":[0],"understanding":[1],"is":[2,27,120],"usually":[3],"challenged":[4],"by":[5,16,117],"the":[6,17,30,75,80,84,88,100,112,124,133],"complementary":[7],"gap":[8],"between":[9],"audio":[10,43,102],"and":[11,44,56],"visual":[12,45],"informative":[13],"bridging.":[14],"Motivated":[15],"recent":[18],"audio-visual":[19,81,118],"studies,":[20],"a":[21,50,92],"closed-set":[22],"word-level":[23],"speech":[24],"recognition":[25,125],"scheme":[26,86,116],"proposed":[28,85,113],"for":[29,79],"Mandarin":[31],"Audio-Visual":[32],"Speech":[33],"Recognition":[34],"(MAVSR)":[35],"Challenge":[36],"in":[37,72],"this":[38],"study.":[39],"To":[40],"achieve":[41],"respective":[42],"encoder":[46,77],"initialization":[47],"more":[48],"effectively,":[49],"3-dimensional":[51],"convolutional":[52],"neural":[53],"network":[54,64],"(CNN)":[55],"an":[57],"attention-based":[58],"bi-directional":[59],"long":[60],"short-term":[61],"memory":[62],"(Bi-LSTM)":[63],"are":[65],"trained.":[66],"With":[67],"two":[68],"fully":[69],"connected":[70],"layers":[71],"addition":[73],"to":[74],"concatenated":[76],"outputs":[78],"joint":[82,114],"training,":[83],"won":[87],"first":[89],"place":[90],"with":[91],"relative":[93],"word":[94],"accuracy":[95],"improvement":[96],"of":[97,122,127],"7.9%":[98],"over":[99],"solitary":[101],"system.":[103],"Experiments":[104],"on":[105],"LRW-1000":[106],"dataset":[107],"have":[108],"substantially":[109],"demonstrated":[110],"that":[111],"training":[115],"incorporation":[119],"capable":[121],"enhancing":[123],"performance":[126],"relatively":[128],"short":[129],"duration":[130],"samples,":[131],"unveiling":[132],"multi-modal":[134],"complementarity.":[135]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}