{"id":"https://openalex.org/W7127052826","doi":"https://doi.org/10.1145/3784833.3784842","title":"ALIGNVSR: AUDIO-VISUAL CROSS-MODAL ALIGNMENT FOR VISUAL SPEECH RECOGNITION","display_name":"ALIGNVSR: AUDIO-VISUAL CROSS-MODAL ALIGNMENT FOR VISUAL SPEECH RECOGNITION","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7127052826","doi":"https://doi.org/10.1145/3784833.3784842"},"language":"en","primary_location":{"id":"doi:10.1145/3784833.3784842","doi":"https://doi.org/10.1145/3784833.3784842","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784842","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"International Conference on Communication and Information Processing (ICCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3784833.3784842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124718694","display_name":"Zehua Liu","orcid":"https://orcid.org/0009-0008-9660-8702","observed_orcids":["https://orcid.org/0009-0008-9660-8702"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9660-8702","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111228895","display_name":"Xiaolou Li","orcid":"https://orcid.org/0009-0001-2307-2096","observed_orcids":["https://orcid.org/0009-0001-2307-2096"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolou Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2307-2096","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124739038","display_name":"Chen Chen","orcid":"https://orcid.org/0009-0003-3698-7636","observed_orcids":["https://orcid.org/0009-0003-3698-7636"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-3698-7636","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124700333","display_name":"Li Guo","orcid":"https://orcid.org/0000-0002-9723-3294","observed_orcids":["https://orcid.org/0000-0002-9723-3294"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9723-3294","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744768","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0002-5546-8060","observed_orcids":["https://orcid.org/0000-0002-5546-8060"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5546-8060","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124711834","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1286-0644","observed_orcids":["https://orcid.org/0000-0002-1286-0644"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1286-0644","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9767,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95157385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9735999703407288,"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":0.9735999703407288,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.008200000040233135,"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":0.0032999999821186066,"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/visual-speech-recognition","display_name":"visual speech recognition","score":1.0},{"id":"https://openalex.org/keywords/lip-movement","display_name":"lip movement","score":0.5960000157356262},{"id":"https://openalex.org/keywords/cross-modal-attention","display_name":"cross-modal attention","score":0.9589999914169312},{"id":"https://openalex.org/keywords/audiovisual-integration","display_name":"audiovisual integration","score":0.5519999861717224},{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.32199999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894999980926514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.696399986743927},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5949000120162964},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435000061988831},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.3073999881744385},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2581999897956848}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3784833.3784842","doi":"https://doi.org/10.1145/3784833.3784842","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784842","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"International Conference on Communication and Information Processing (ICCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.16438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.16438","pdf_url":"https://arxiv.org/pdf/2410.16438","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2410.16438","doi":"https://doi.org/10.48550/arxiv.2410.16438","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.16438","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3784833.3784842","doi":"https://doi.org/10.1145/3784833.3784842","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784842","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"International Conference on Communication and Information Processing (ICCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127052826.pdf","grobid_xml":"https://content.openalex.org/works/W7127052826.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2550980560","https://openalex.org/W2596627958","https://openalex.org/W2766219058","https://openalex.org/W2883383043","https://openalex.org/W2943235166","https://openalex.org/W2949662773","https://openalex.org/W3097777922","https://openalex.org/W3162293946","https://openalex.org/W3169320628","https://openalex.org/W4307286264","https://openalex.org/W4312638101","https://openalex.org/W4372346152","https://openalex.org/W4390872483","https://openalex.org/W4392904696","https://openalex.org/W4402111743","https://openalex.org/W4402112118"],"related_works":["https://openalex.org/W4402112118","https://openalex.org/W3205193540","https://openalex.org/W3011234510","https://openalex.org/W4390691978","https://openalex.org/W4385767994","https://openalex.org/W3163456394","https://openalex.org/W4372260478","https://openalex.org/W4390872483","https://openalex.org/W4415524539","https://openalex.org/W4392901809"],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"(VSR)":[3],"aims":[4],"to":[5,17,80,103,126],"recognize":[6],"corresponding":[7],"text":[8],"by":[9],"analyzing":[10],"visual":[11,78],"information":[12,23,33,65],"from":[13,34,100],"lip":[14,25],"movements.":[15],"Due":[16],"the":[18,59,69,75,85,112,128,132,135,141],"high":[19],"variability":[20],"and":[21,37,67,71,77,93,117,143,158],"weak":[22],"of":[24,106,134],"movements,":[26],"VSR":[27,47,153],"tasks":[28],"require":[29],"effectively":[30],"utilizing":[31],"any":[32,35,39],"source":[36,66],"at":[38],"level.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"a":[46,96,104,119],"method":[48,57,86],"based":[49,110],"on":[50,111,140],"audio-visual":[51],"cross-modal":[52,97],"alignment,":[53,130],"named":[54],"AlignVSR.":[55],"The":[56],"leverages":[58],"audio":[60,76,94,107,116,136],"modality":[61],"as":[62],"an":[63],"auxiliary":[64],"utilizes":[68],"global":[70,89,129],"local":[72,121],"correspondence":[73,114],"between":[74,91,115],"modalities":[79],"improve":[81],"visual-to-text":[82],"inference.":[83],"Specifically,":[84],"first":[87],"captures":[88],"alignment":[90,122],"video":[92,101],"through":[95],"attention":[98],"mechanism":[99],"frames":[102],"bank":[105],"units.":[108],"Then,":[109],"temporal":[113],"video,":[118],"frame-level":[120],"loss":[123],"is":[124],"introduced":[125],"refine":[127],"improving":[131],"utility":[133],"information.":[137],"Experimental":[138],"results":[139],"LRS2":[142],"CNVSRC.Single":[144],"datasets":[145],"consistently":[146],"show":[147],"that":[148],"AlignVSR":[149],"outperforms":[150],"several":[151],"mainstream":[152],"methods,":[154],"demonstrating":[155],"its":[156],"superior":[157],"robust":[159],"performance.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-03T00:00:00"}