{"id":"https://openalex.org/W4415708109","doi":"https://doi.org/10.1109/icme59968.2025.11210211","title":"Align-AV-HuBERT: AV-HuBERT with Audio-Visual Temporal Alignment","display_name":"Align-AV-HuBERT: AV-HuBERT with Audio-Visual Temporal Alignment","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708109","doi":"https://doi.org/10.1109/icme59968.2025.11210211"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5113355139","display_name":"Cancan Li","orcid":"https://orcid.org/0009-0002-2537-6293"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cancan Li","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China,430072"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052100570","display_name":"Fei Su","orcid":"https://orcid.org/0000-0002-3529-9845"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China,430072"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100446344","display_name":"Juan Liu","orcid":"https://orcid.org/0000-0003-4963-6694"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Liu","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University,Wuhan,China,430072"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113355139"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4237128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9818999767303467,"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":0.9818999767303467,"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":0.005900000222027302,"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/T11309","display_name":"Music and Audio Processing","score":0.002199999988079071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4618000090122223},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4429999887943268},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4377000033855438},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.424699991941452},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.33799999952316284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3359000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748000025749207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7120000123977661},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5382000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311999917030334},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.424699991941452},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.32910001277923584},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2702000141143799}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2604379605","https://openalex.org/W2808631503","https://openalex.org/W3015830103","https://openalex.org/W3142098745","https://openalex.org/W3160799772","https://openalex.org/W3162293946","https://openalex.org/W3167917117","https://openalex.org/W3209059054","https://openalex.org/W4289946024","https://openalex.org/W4297841713","https://openalex.org/W4372266552","https://openalex.org/W4372346152","https://openalex.org/W4380373744","https://openalex.org/W4384661029","https://openalex.org/W4386071707","https://openalex.org/W4401597893","https://openalex.org/W4402112118","https://openalex.org/W4402352712","https://openalex.org/W4403791608","https://openalex.org/W4408345615"],"related_works":[],"abstract_inverted_index":{"Lip":[0],"movement":[1],"and":[2,12,29,48,86,95,104,119,140],"acoustic":[3],"information":[4],"complement":[5],"each":[6],"other":[7],"in":[8,18,55],"speech":[9],"recognition":[10],"tasks,":[11],"audio-visual":[13,24,83],"models":[14,25,60,141],"have":[15],"significantly":[16],"advanced":[17],"recent":[19],"years.":[20],"However,":[21],"most":[22],"existing":[23],"assume":[26],"that":[27,80],"audio":[28,47,103,118],"video":[30,105,120],"inputs":[31],"are":[32,39,142],"temporally":[33],"aligned.":[34],"In":[35,65],"practical":[36],"applications,":[37],"there":[38],"often":[40],"scenarios":[41],"where":[42],"time":[43],"deviations":[44],"occur":[45],"between":[46],"video,":[49],"leading":[50],"to":[51],"a":[52,71],"substantial":[53],"decline":[54],"the":[56,110,127,133],"performance":[57,125],"of":[58,132],"previous":[59],"when":[61,114],"alignment":[62,85,93],"is":[63],"disrupted.":[64],"this":[66],"paper,":[67],"we":[68],"propose":[69],"Align-AV-HuBERT,":[70],"model":[72],"based":[73],"on":[74,101,116],"Audio-Visual":[75],"Hidden":[76],"Unit":[77],"BERT":[78],"(AV-HuBERT)":[79],"simultaneously":[81],"achieves":[82],"temporal":[84],"self-supervised":[87],"learning":[88],"by":[89],"training":[90],"with":[91,109],"both":[92],"loss":[94],"masked":[96],"prediction":[97],"loss.":[98],"When":[99],"evaluated":[100],"aligned":[102],"datasets,":[106,121],"Align-AV-HuBERT":[107,122],"matches":[108],"AV-HuBERT":[111,134],"baseline.":[112],"Moreover,":[113],"tested":[115],"unaligned":[117],"maintains":[123],"stable":[124],"while":[126],"Word":[128],"Error":[129],"Rate":[130],"(WER)":[131],"baseline":[135],"increases":[136],"dramatically.":[137],"Our":[138],"code":[139],"available":[143],"at":[144],"https://github.com/lilycalre/Align-AV-HuBERT.":[145]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}