{"id":"https://openalex.org/W4375868850","doi":"https://doi.org/10.1109/icassp49357.2023.10095582","title":"Lip-to-Speech Synthesis in the Wild with Multi-Task Learning","display_name":"Lip-to-Speech Synthesis in the Wild with Multi-Task Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868850","doi":"https://doi.org/10.1109/icassp49357.2023.10095582"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454455","display_name":"Joanna Hong","orcid":"https://orcid.org/0000-0001-9683-1260"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joanna Hong","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9951000213623047,"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":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.8325487971305847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7239011526107788},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6621970534324646},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6433636546134949},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5503732562065125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088586807250977},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48358577489852905},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47281375527381897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4327929615974426},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4264851212501526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8325487971305847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7239011526107788},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6621970534324646},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6433636546134949},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5503732562065125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088586807250977},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48358577489852905},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47281375527381897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4327929615974426},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4264851212501526},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2067295501","https://openalex.org/W2120847449","https://openalex.org/W2127141656","https://openalex.org/W2516001803","https://openalex.org/W2551572271","https://openalex.org/W2752796333","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2963250244","https://openalex.org/W2963654155","https://openalex.org/W2963799213","https://openalex.org/W2964352155","https://openalex.org/W2972563022","https://openalex.org/W3035626590","https://openalex.org/W3096650361","https://openalex.org/W3097777922","https://openalex.org/W3157840621","https://openalex.org/W3162293946","https://openalex.org/W3205193540","https://openalex.org/W3211862173","https://openalex.org/W3213322812","https://openalex.org/W4224319127","https://openalex.org/W4296069328","https://openalex.org/W6734491695","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6757817989","https://openalex.org/W6794378236","https://openalex.org/W6803359641","https://openalex.org/W6810661184"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W596245619","https://openalex.org/W2254895521","https://openalex.org/W2251422729"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2,20],"shown":[3],"impressive":[4],"performance":[5],"in":[6,27,48,70],"Lip-to-speech":[7],"synthesis":[8],"that":[9,57,81],"aims":[10],"to":[11,31,38,92],"reconstruct":[12,59],"speech":[13,26,60,112],"from":[14,23,44,64],"visual":[15],"information":[16],"alone.":[17],"However,":[18],"they":[19],"been":[21],"suffering":[22],"synthesizing":[24,111],"accurate":[25],"the":[28,36,40,45,65,83,94,104,108,114,125,128],"wild,":[29],"due":[30],"insufficient":[32,95],"supervision":[33],"for":[34],"guiding":[35],"model":[37,84],"infer":[39],"correct":[41,62],"content.":[42],"Distinct":[43],"previous":[46],"methods,":[47],"this":[49,75],"paper,":[50],"we":[51,77],"develop":[52],"a":[53,71],"powerful":[54],"Lip2Speech":[55],"method":[56,130],"can":[58],"with":[61,120],"contents":[63],"input":[66],"lip":[67],"movements,":[68],"even":[69],"wild":[72],"environment.":[73],"To":[74],"end,":[76],"design":[78],"multitask":[79],"learning":[80],"guides":[82],"using":[85,131],"multimodal":[86],"supervision,":[87],"i.e.":[88],"text":[89],"and":[90,134],"audio,":[91],"complement":[93],"word":[96],"representations":[97],"of":[98,110,117,127],"acoustic":[99],"feature":[100],"reconstruction":[101],"loss.":[102],"Thus,":[103],"proposed":[105,129],"framework":[106],"brings":[107],"advantage":[109],"containing":[113],"right":[115],"content":[116],"multiple":[118],"speakers":[119],"unconstrained":[121],"sentences.":[122],"We":[123],"verify":[124],"effectiveness":[126],"LRS2,":[132],"LRS3,":[133],"LRW":[135],"datasets.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}