{"id":"https://openalex.org/W4283798744","doi":"https://doi.org/10.1609/aaai.v36i3.20210","title":"Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation","display_name":"Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4283798744","doi":"https://doi.org/10.1609/aaai.v36i3.20210"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v36i3.20210","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i3.20210","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20210/19969","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20210/19969","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100838868","display_name":"Chih-Chun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Chun Yang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan, R.O.C","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022911737","display_name":"Wan-Cyuan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wan-Cyuan Fan","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103056761","display_name":"Cheng-Fu Yang","orcid":"https://orcid.org/0000-0002-6916-2142"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Fu Yang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan, R.O.C","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090045508","display_name":"Yu-Chiang Frank Wang","orcid":"https://orcid.org/0000-0002-2333-157X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C.\nASUS Intelligent Cloud Services, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan, R.O.C.\nASUS Intelligent Cloud Services, Taiwan, R.O.C","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100838868"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.7009,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87031791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"36","issue":"3","first_page":"3036","last_page":"3044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9922000169754028,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7436050176620483},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6842755675315857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6788036823272705},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5165570974349976},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5065790414810181},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46377983689308167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4564845561981201},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44391703605651855},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4371849000453949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42796605825424194},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20612332224845886},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14846506714820862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436050176620483},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6842755675315857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6788036823272705},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5165570974349976},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5065790414810181},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46377983689308167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4564845561981201},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44391703605651855},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4371849000453949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42796605825424194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20612332224845886},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14846506714820862},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v36i3.20210","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i3.20210","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20210/19969","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v36i3.20210","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i3.20210","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20210/19969","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1001751934","display_name":null,"funder_award_id":"MOST 110-2221-E-002-121","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G361372759","display_name":null,"funder_award_id":"110-26","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G8056139164","display_name":null,"funder_award_id":"110-2634-F-002-052","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283798744.pdf","grobid_xml":"https://content.openalex.org/works/W4283798744.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2120847449","https://openalex.org/W2327501763","https://openalex.org/W2777302760","https://openalex.org/W2785077884","https://openalex.org/W2796931171","https://openalex.org/W2883082281","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2898926657","https://openalex.org/W2903739847","https://openalex.org/W2944294033","https://openalex.org/W2962974898","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2964559396","https://openalex.org/W2972659941","https://openalex.org/W2972849140","https://openalex.org/W2981501041","https://openalex.org/W2981767644","https://openalex.org/W2987346570","https://openalex.org/W2989671705","https://openalex.org/W2996970093","https://openalex.org/W3003133812","https://openalex.org/W3006974783","https://openalex.org/W3016011581","https://openalex.org/W3024559545","https://openalex.org/W3035626590","https://openalex.org/W3081492798","https://openalex.org/W3089795913","https://openalex.org/W3103322708","https://openalex.org/W3105763085","https://openalex.org/W3119418740","https://openalex.org/W3167917117","https://openalex.org/W4287392530","https://openalex.org/W6734491695","https://openalex.org/W6738591926","https://openalex.org/W6750008037","https://openalex.org/W6754392867","https://openalex.org/W6757079273"],"related_works":["https://openalex.org/W4386721968","https://openalex.org/W2613123485","https://openalex.org/W4205137593","https://openalex.org/W2952745240","https://openalex.org/W4236838349","https://openalex.org/W2949074159","https://openalex.org/W4301143707","https://openalex.org/W4298715519","https://openalex.org/W2012466265","https://openalex.org/W3198037411"],"abstract_inverted_index":{"As":[0],"a":[1,20,41,131],"key":[2],"characteristic":[3],"in":[4],"audio-visual":[5,142],"speech":[6,26],"recognition":[7,27,110],"(AVSR),":[8],"relating":[9],"linguistic":[10,66,73,101],"information":[11],"observed":[12],"across":[13],"visual":[14,63,91],"and":[15,83,90,100,111],"audio":[16,89],"data":[17,33,92],"has":[18],"been":[19],"challenge,":[21],"benefiting":[22],"not":[23,75],"only":[24,76],"audio/visual":[25],"(ASR/VSR)":[28],"but":[29,85],"also":[30,86],"for":[31,45],"manipulating":[32],"within/across":[34],"modalities.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"present":[40],"feature":[42],"disentanglement-based":[43],"framework":[44],"jointly":[46,138],"addressing":[47],"the":[48,96,140],"above":[49],"tasks.":[50,144],"By":[51],"advancing":[52],"cross-modal":[53],"mutual":[54],"learning":[55,143],"strategies,":[56],"our":[57,117],"model":[58,118],"is":[59,130,135],"able":[60,136],"to":[61,79,87,114,137],"convert":[62],"or":[64],"audio-based":[65],"features":[67],"into":[68],"modality-agnostic":[69],"representations.":[70],"Such":[71],"derived":[72],"representations":[74],"allow":[77],"one":[78],"perform":[80,105],"ASR,":[81],"VSR,":[82],"AVSR,":[84],"manipulate":[88],"output":[93],"based":[94],"on":[95,108,124],"desirable":[97],"subject":[98],"identity":[99],"content":[102],"information.":[103],"We":[104],"extensive":[106],"experiments":[107],"different":[109],"synthesis":[112],"tasks":[113],"show":[115],"that":[116,134],"performs":[119],"favorably":[120],"against":[121],"state-of-the-art":[122],"approaches":[123],"each":[125],"individual":[126],"task,":[127],"while":[128],"ours":[129],"unified":[132],"solution":[133],"tackle":[139],"aforementioned":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
