{"id":"https://openalex.org/W7169676157","doi":"https://doi.org/10.1007/978-981-92-3429-5_15","title":"Self-supervised Cross-Modal Alignment for High-Fidelity Audio-Driven Lip Sync with Latent Diffusion","display_name":"Self-supervised Cross-Modal Alignment for High-Fidelity Audio-Driven Lip Sync with Latent Diffusion","publication_year":2026,"publication_date":"2026-07-18","ids":{"openalex":"https://openalex.org/W7169676157","doi":"https://doi.org/10.1007/978-981-92-3429-5_15"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-3429-5_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3429-5_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5010453430","display_name":"Zhiyue Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyue Chen","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064583442","display_name":"Minjie Bian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minjie Bian","raw_affiliation_strings":["Shanghai Data Group, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Data Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084467125","display_name":"Huahu Xu","orcid":"https://orcid.org/0000-0001-8220-1639"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huahu Xu","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886812","display_name":"Hailan Wang","orcid":"https://orcid.org/0000-0002-4740-4606"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailan Wang","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5141138423","display_name":"Xueping Man","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueping Man","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5084467125"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7318999767303467},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5454000234603882},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.4828000068664551},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44909998774528503},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.36059999465942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677999973297119},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7318999767303467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5896000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608999729156494},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5454000234603882},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.4828000068664551},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41429999470710754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-3429-5_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3429-5_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2064076387","https://openalex.org/W2551572271","https://openalex.org/W2790228436","https://openalex.org/W2808631503","https://openalex.org/W2962785568","https://openalex.org/W3019952993","https://openalex.org/W3186090335","https://openalex.org/W3209059054","https://openalex.org/W3210458411","https://openalex.org/W3211054674","https://openalex.org/W4312933868","https://openalex.org/W4386072021","https://openalex.org/W4394597155","https://openalex.org/W4402727293","https://openalex.org/W4403791206","https://openalex.org/W4404199654","https://openalex.org/W4413007916","https://openalex.org/W4416251291","https://openalex.org/W7117163720","https://openalex.org/W7130393018","https://openalex.org/W7133218093"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-20T05:51:44.042241","created_date":"2026-07-19T00:00:00"}
