{"id":"https://openalex.org/W4392780157","doi":"https://doi.org/10.1109/tpami.2024.3376710","title":"Deep Learning for Visual Speech Analysis: A Survey","display_name":"Deep Learning for Visual Speech Analysis: A Survey","publication_year":2024,"publication_date":"2024-03-13","ids":{"openalex":"https://openalex.org/W4392780157","doi":"https://doi.org/10.1109/tpami.2024.3376710","pmid":"https://pubmed.ncbi.nlm.nih.gov/38478434"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3376710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3376710","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","pubmed"],"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/A5007427128","display_name":"Changchong Sheng","orcid":"https://orcid.org/0000-0001-6255-754X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I2800710378","display_name":"Naval University of Engineering","ror":"https://ror.org/056vyez31","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800710378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changchong Sheng","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","National Key Laboratory of Electromagnetic Energy, Naval University of Engineering, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Laboratory of Electromagnetic Energy, Naval University of Engineering, China","institution_ids":["https://openalex.org/I2800710378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082887216","display_name":"Gangyao Kuang","orcid":"https://orcid.org/0000-0003-2620-889X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangyao Kuang","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088685596","display_name":"Liang Bai","orcid":"https://orcid.org/0000-0002-7667-6539"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Bai","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091529433","display_name":"Chenping Hou","orcid":"https://orcid.org/0000-0002-9335-0469"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenping Hou","raw_affiliation_strings":["College of Liberal Arts and Sciences, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Liberal Arts and Sciences, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013644792","display_name":"Yulan Guo","orcid":"https://orcid.org/0000-0003-0952-476X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulan Guo","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014611768","display_name":"Matti Pietik\u00e4inen","orcid":"https://orcid.org/0000-0003-2263-6731"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matti Pietik\u00e4inen","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis, Oulu University, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, Oulu University, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5007427128"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I2800710378"],"apc_list":null,"apc_paid":null,"fwci":13.6208,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.99374569,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"9","first_page":"6001","last_page":"6022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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":0.7696535587310791},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7191908359527588},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5414796471595764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5267464518547058},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46703124046325684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3542812168598175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3301117420196533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696535587310791},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7191908359527588},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5414796471595764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267464518547058},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46703124046325684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3542812168598175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3301117420196533},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3376710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3376710","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38478434","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38478434","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1761424634","display_name":null,"funder_award_id":"61872379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2443591357","display_name":"LESLearn: Label, Energy and Sample Efficient Feature Representation and Learning in Computer Vision","funder_award_id":"331883","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G5616526104","display_name":null,"funder_award_id":"2021YFB3100800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7774348999","display_name":null,"funder_award_id":"62376283","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8008312880","display_name":null,"funder_award_id":"331883","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":206,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W1490506669","https://openalex.org/W1503933356","https://openalex.org/W1526392145","https://openalex.org/W1569907127","https://openalex.org/W1922655562","https://openalex.org/W1962124124","https://openalex.org/W1992057917","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2017107803","https://openalex.org/W2060510034","https://openalex.org/W2070726616","https://openalex.org/W2080277992","https://openalex.org/W2083792893","https://openalex.org/W2096391593","https://openalex.org/W2102443632","https://openalex.org/W2106284211","https://openalex.org/W2113814270","https://openalex.org/W2114336453","https://openalex.org/W2120067677","https://openalex.org/W2121486117","https://openalex.org/W2124765650","https://openalex.org/W2125389028","https://openalex.org/W2127141656","https://openalex.org/W2129360799","https://openalex.org/W2138621090","https://openalex.org/W2143612262","https://openalex.org/W2146991130","https://openalex.org/W2147885303","https://openalex.org/W2162220380","https://openalex.org/W2194775991","https://openalex.org/W2301937176","https://openalex.org/W2327501763","https://openalex.org/W2338517121","https://openalex.org/W2513140567","https://openalex.org/W2513259840","https://openalex.org/W2551572271","https://openalex.org/W2570575067","https://openalex.org/W2585824449","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2752782242","https://openalex.org/W2782422271","https://openalex.org/W2790649793","https://openalex.org/W2799930024","https://openalex.org/W2806833697","https://openalex.org/W2808631503","https://openalex.org/W2886564777","https://openalex.org/W2886945201","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2891226622","https://openalex.org/W2895226286","https://openalex.org/W2897318954","https://openalex.org/W2897492880","https://openalex.org/W2904573504","https://openalex.org/W2914217321","https://openalex.org/W2942074357","https://openalex.org/W2944294033","https://openalex.org/W2950864153","https://openalex.org/W2962960500","https://openalex.org/W2963019222","https://openalex.org/W2963030892","https://openalex.org/W2963073614","https://openalex.org/W2963076818","https://openalex.org/W2963081548","https://openalex.org/W2963082324","https://openalex.org/W2963092440","https://openalex.org/W2963115079","https://openalex.org/W2963240019","https://openalex.org/W2963290645","https://openalex.org/W2963446712","https://openalex.org/W2963524571","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963680395","https://openalex.org/W2963744813","https://openalex.org/W2963822910","https://openalex.org/W2964095416","https://openalex.org/W2964207404","https://openalex.org/W2964283370","https://openalex.org/W2964449965","https://openalex.org/W2964559396","https://openalex.org/W2969985801","https://openalex.org/W2970270554","https://openalex.org/W2971634123","https://openalex.org/W2972756321","https://openalex.org/W2972775954","https://openalex.org/W2973085229","https://openalex.org/W2979894294","https://openalex.org/W2980562267","https://openalex.org/W2981263323","https://openalex.org/W2981501041","https://openalex.org/W2981767644","https://openalex.org/W2982058372","https://openalex.org/W2990452356","https://openalex.org/W2996970093","https://openalex.org/W3001079424","https://openalex.org/W3006974783","https://openalex.org/W3010434693","https://openalex.org/W3015383493","https://openalex.org/W3015814181","https://openalex.org/W3015830103","https://openalex.org/W3016011332","https://openalex.org/W3016011581","https://openalex.org/W3016663370","https://openalex.org/W3019952993","https://openalex.org/W3023351797","https://openalex.org/W3023706973","https://openalex.org/W3034211329","https://openalex.org/W3081492798","https://openalex.org/W3086926995","https://openalex.org/W3089177030","https://openalex.org/W3089455867","https://openalex.org/W3093450153","https://openalex.org/W3095622232","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3101257721","https://openalex.org/W3101631197","https://openalex.org/W3103322708","https://openalex.org/W3103801904","https://openalex.org/W3105763085","https://openalex.org/W3109114891","https://openalex.org/W3109585842","https://openalex.org/W3122663073","https://openalex.org/W3126911614","https://openalex.org/W3154411171","https://openalex.org/W3158779148","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3168997536","https://openalex.org/W3174763799","https://openalex.org/W3175342695","https://openalex.org/W3175779516","https://openalex.org/W3176721746","https://openalex.org/W3186090335","https://openalex.org/W3186700381","https://openalex.org/W3187364420","https://openalex.org/W3188692592","https://openalex.org/W3192072773","https://openalex.org/W3192148059","https://openalex.org/W3194006130","https://openalex.org/W3195529437","https://openalex.org/W3197087768","https://openalex.org/W3197199219","https://openalex.org/W3197567540","https://openalex.org/W3199527474","https://openalex.org/W3207628370","https://openalex.org/W3207849023","https://openalex.org/W3208601549","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4200630629","https://openalex.org/W4200631136","https://openalex.org/W4206517532","https://openalex.org/W4210657261","https://openalex.org/W4213019189","https://openalex.org/W4225305629","https://openalex.org/W4236398794","https://openalex.org/W4283798744","https://openalex.org/W4297841713","https://openalex.org/W4298112588","https://openalex.org/W4309876056","https://openalex.org/W4312444931","https://openalex.org/W4312638101","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4385822729","https://openalex.org/W4386072021","https://openalex.org/W4386076250","https://openalex.org/W4390874181","https://openalex.org/W6628877408","https://openalex.org/W6637373629","https://openalex.org/W6640090968","https://openalex.org/W6678815747","https://openalex.org/W6684191040","https://openalex.org/W6725923168","https://openalex.org/W6729383884","https://openalex.org/W6732872814","https://openalex.org/W6737664043","https://openalex.org/W6737896281","https://openalex.org/W6739901393","https://openalex.org/W6748181857","https://openalex.org/W6749251296","https://openalex.org/W6751750676","https://openalex.org/W6752888775","https://openalex.org/W6754048563","https://openalex.org/W6754420807","https://openalex.org/W6757599822","https://openalex.org/W6763296340","https://openalex.org/W6767264202","https://openalex.org/W6767349417","https://openalex.org/W6774285787","https://openalex.org/W6776963518","https://openalex.org/W6785851975","https://openalex.org/W6803206414","https://openalex.org/W6847187194","https://openalex.org/W6849049266"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Visual":[0],"speech,":[1,8,80,105],"referring":[2],"to":[3,14,59],"the":[4,40,47],"visual":[5,43,68,79,96,104],"domain":[6],"of":[7,42,88,103,114],"has":[9],"attracted":[10],"increasing":[11],"attention":[12],"due":[13],"its":[15],"wide":[16],"applications,":[17],"such":[18],"as":[19],"public":[20],"security,":[21],"medical":[22],"treatment,":[23],"military":[24],"defense,":[25],"and":[26,71,117,128],"film":[27],"entertainment.":[28],"As":[29],"a":[30,85,112],"powerful":[31],"AI":[32],"strategy,":[33],"deep":[34,52,92],"learning":[35,53,93],"techniques":[36],"have":[37,56],"extensively":[38],"promoted":[39],"development":[41],"speech":[44,69,97],"learning.":[45],"Over":[46],"past":[48],"five":[49],"years,":[50],"numerous":[51],"based":[54],"methods":[55,94],"been":[57],"proposed":[58],"address":[60],"various":[61],"problems":[62],"in":[63,91,125],"this":[64,81],"area,":[65],"especially":[66],"automatic":[67],"recognition":[70],"generation.":[72],"To":[73],"push":[74],"forward":[75],"future":[76,131],"research":[77,127,132],"on":[78,95],"paper":[82],"will":[83],"present":[84],"comprehensive":[86],"review":[87],"recent":[89],"progress":[90],"analysis.":[98],"We":[99],"cover":[100],"different":[101],"aspects":[102],"including":[106],"fundamental":[107],"problems,":[108],"challenges,":[109],"benchmark":[110],"datasets,":[111],"taxonomy":[113],"existing":[115],"methods,":[116],"state-of-the-art":[118],"performance.":[119],"Besides,":[120],"we":[121],"also":[122],"identify":[123],"gaps":[124],"current":[126],"discuss":[129],"inspiring":[130],"directions.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":14}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}