{"id":"https://openalex.org/W4200635083","doi":"https://doi.org/10.1109/tnnls.2022.3191677","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","display_name":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","publication_year":2022,"publication_date":"2022-07-22","ids":{"openalex":"https://openalex.org/W4200635083","doi":"https://doi.org/10.1109/tnnls.2022.3191677","pmid":"https://pubmed.ncbi.nlm.nih.gov/35867361"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3191677","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3191677","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tnnls.2022.3191677","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023714181","display_name":"Leyuan Qu","orcid":"https://orcid.org/0000-0001-6694-5355"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Leyuan Qu","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Institute, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6694-5355","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Institute, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Institute, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5163-938X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Institute, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Institute, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1343-4775","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Institute, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023714181"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":4.9102,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95963976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"35","issue":"2","first_page":"2772","last_page":"2782"},"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/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"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":0.7993846535682678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7297539710998535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4886529743671417},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4631485342979431},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4536331593990326},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4482019543647766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3598639965057373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993846535682678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7297539710998535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4886529743671417},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4631485342979431},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4536331593990326},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4482019543647766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3598639965057373},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"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":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2022.3191677","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3191677","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35867361","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35867361","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 neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2112.04748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.04748","pdf_url":"https://arxiv.org/pdf/2112.04748","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/tnnls.2022.3191677","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3191677","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":116,"referenced_works":["https://openalex.org/W16682072","https://openalex.org/W123135133","https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1533861849","https://openalex.org/W1552314771","https://openalex.org/W1614298861","https://openalex.org/W1984483979","https://openalex.org/W2008120082","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2049686551","https://openalex.org/W2061960534","https://openalex.org/W2106284211","https://openalex.org/W2120847449","https://openalex.org/W2127141656","https://openalex.org/W2133906911","https://openalex.org/W2134800885","https://openalex.org/W2140647972","https://openalex.org/W2159089611","https://openalex.org/W2267805933","https://openalex.org/W2293856338","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2341528187","https://openalex.org/W2411745509","https://openalex.org/W2471520273","https://openalex.org/W2487442924","https://openalex.org/W2512544816","https://openalex.org/W2516001803","https://openalex.org/W2519091744","https://openalex.org/W2551572271","https://openalex.org/W2585824449","https://openalex.org/W2594690981","https://openalex.org/W2619697695","https://openalex.org/W2625027024","https://openalex.org/W2714726990","https://openalex.org/W2735762732","https://openalex.org/W2767459507","https://openalex.org/W2770785043","https://openalex.org/W2785325870","https://openalex.org/W2808631503","https://openalex.org/W2889048668","https://openalex.org/W2890052321","https://openalex.org/W2890413327","https://openalex.org/W2890952074","https://openalex.org/W2896457183","https://openalex.org/W2897492880","https://openalex.org/W2913144232","https://openalex.org/W2947883281","https://openalex.org/W2950864153","https://openalex.org/W2950936614","https://openalex.org/W2952746495","https://openalex.org/W2963019222","https://openalex.org/W2963030892","https://openalex.org/W2963115079","https://openalex.org/W2963300588","https://openalex.org/W2963356069","https://openalex.org/W2963426332","https://openalex.org/W2963528589","https://openalex.org/W2963894079","https://openalex.org/W2963936489","https://openalex.org/W2964243274","https://openalex.org/W2964283370","https://openalex.org/W2964352155","https://openalex.org/W2972563022","https://openalex.org/W2972756321","https://openalex.org/W2972852451","https://openalex.org/W2973085229","https://openalex.org/W2973215447","https://openalex.org/W2996428491","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3011959832","https://openalex.org/W3016011581","https://openalex.org/W3024147341","https://openalex.org/W3034999214","https://openalex.org/W3035626590","https://openalex.org/W3086926995","https://openalex.org/W3091641623","https://openalex.org/W3096214032","https://openalex.org/W3096650361","https://openalex.org/W3096806995","https://openalex.org/W3101998545","https://openalex.org/W3103801904","https://openalex.org/W3128750130","https://openalex.org/W3158986867","https://openalex.org/W4250689965","https://openalex.org/W4252708392","https://openalex.org/W4287199820","https://openalex.org/W4287608901","https://openalex.org/W4288088047","https://openalex.org/W4289761690","https://openalex.org/W4293862381","https://openalex.org/W4298112588","https://openalex.org/W4300503772","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631943919","https://openalex.org/W6636510571","https://openalex.org/W6679855610","https://openalex.org/W6732872814","https://openalex.org/W6747899497","https://openalex.org/W6750475725","https://openalex.org/W6751887642","https://openalex.org/W6752203281","https://openalex.org/W6754048563","https://openalex.org/W6754473786","https://openalex.org/W6755207826","https://openalex.org/W6763296340","https://openalex.org/W6768021236","https://openalex.org/W6769311223","https://openalex.org/W6785011006"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W2942893872","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"The":[0,57],"aim":[1],"of":[2,10,23,35,80],"this":[3],"work":[4],"is":[5,61],"to":[6,43,48,111,121,136],"investigate":[7],"the":[8,20,78,81,87,129,138,145,153,164],"impact":[9,139],"crossmodal":[11],"self-supervised":[12],"pre-training":[13],"for":[14,96],"speech":[15,98,106,126,159],"reconstruction":[16,99,127],"(video-to-audio)":[17],"by":[18,151],"leveraging":[19],"natural":[21],"co-occurrence":[22],"audio":[24],"and":[25,39,71,94,100,108,116,162,170],"visual":[26],"streams":[27],"in":[28,114],"videos.":[29],"We":[30],"propose":[31],"LipSound2":[32,59],"that":[33],"consists":[34],"an":[36],"encoder-decoder":[37],"architecture":[38],"location-aware":[40],"attention":[41],"mechanism":[42],"map":[44],"face":[45],"image":[46],"sequences":[47],"mel-scale":[49],"spectrograms":[50],"directly":[51],"without":[52],"requiring":[53],"any":[54],"human":[55],"annotations.":[56],"proposed":[58,82],"model":[60,89],"first":[62],"pre-trained":[63,88,158],"on":[64,90,105,128,140,156,167],"\u223c":[65],"2400":[66],"-h":[67],"multilingual":[68],"(e.g.,":[69],"English":[70,97,169],"German)":[72],"audio-visual":[73],"data":[74],"(VoxCeleb2).":[75],"To":[76],"verify":[77,137],"generalizability":[79],"method,":[83],"we":[84,123,143],"then":[85],"fine-tune":[86],"domain-specific":[91],"datasets":[92],"(GRID":[93],"TCD-TIMIT)":[95],"achieve":[101,163],"a":[102,157],"significant":[103],"improvement":[104],"quality":[107],"intelligibility":[109],"compared":[110],"previous":[112],"approaches":[113],"speaker-dependent":[115],"speaker-independent":[117],"settings.":[118],"In":[119],"addition":[120],"English,":[122],"conduct":[124],"Chinese":[125,130,171],"Mandarin":[131],"Lip":[132],"Reading":[133],"(CMLR)":[134],"dataset":[135],"transferability.":[141],"Finally,":[142],"train":[144],"cascaded":[146],"lip":[147],"reading":[148],"(video-to-text)":[149],"system":[150,161],"fine-tuning":[152],"generated":[154],"audios":[155],"recognition":[160],"state-of-the-art":[165],"performance":[166],"both":[168],"benchmark":[172],"datasets.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}