{"id":"https://openalex.org/W7154245386","doi":"https://doi.org/10.1109/tip.2026.3682022","title":"Emphasizing Domain Differences Through Interactive-Augmented Prompts in Continual Audio-Visual Speech Recognition","display_name":"Emphasizing Domain Differences Through Interactive-Augmented Prompts in Continual Audio-Visual Speech Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154245386","doi":"https://doi.org/10.1109/tip.2026.3682022","pmid":"https://pubmed.ncbi.nlm.nih.gov/41979971"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3682022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3682022","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101485171","display_name":"Dongjie Fu","orcid":"https://orcid.org/0009-0000-7682-7678"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjie Fu","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0000-7682-7678","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingyuan Chen","orcid":"https://orcid.org/0000-0003-0415-6937"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Chen","raw_affiliation_strings":["College of Education, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0415-6937","affiliations":[{"raw_affiliation_string":"College of Education, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011966","display_name":"Tao Jin","orcid":"https://orcid.org/0000-0003-3564-1628"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jin","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0003-3564-1628","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036747535","display_name":"Zhongfei Zhang","orcid":"https://orcid.org/0000-0001-5098-2506"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongfei Zhang","raw_affiliation_strings":["Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5098-2506","affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46497389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4269","last_page":"4279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7656000256538391,"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":0.7656000256538391,"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":0.06530000269412994,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.046799998730421066,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5450999736785889},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41350001096725464},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3741999864578247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37059998512268066},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.3702999949455261},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3425000011920929},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33570000529289246},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3027999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071999907493591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6869999766349792},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49570000171661377},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3905999958515167},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25049999356269836}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3682022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3682022","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41979971","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41979971","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-Visual":[0,97],"Speech":[1,98],"Recognition":[2,99],"(AVSR)":[3],"has":[4],"been":[5],"studied":[6],"for":[7,31,115,130,137,260,301,306],"a":[8,28,106,112,189,242],"long":[9],"time":[10],"in":[11,77,285,296,315],"the":[12,16,51,82,86,95,131,138,156,172,179,253,269,292,304],"literature.":[13],"By":[14],"leveraging":[15],"complementary":[17],"information":[18],"from":[19,207],"both":[20,150],"acoustic":[21],"and":[22,63,70,80,141,161,166,193,200,226,230,309],"visual":[23,139],"modalities,":[24],"this":[25,91],"approach":[26],"offers":[27],"promising":[29],"solution":[30],"robust":[32,308],"speech":[33,312],"transcription.":[34],"While":[35],"recent":[36],"AVSR":[37,104],"models":[38],"have":[39],"achieved":[40],"impressive":[41],"performance":[42,284],"on":[43,268],"large-scale,":[44],"uniformly":[45],"distributed":[46],"datasets,":[47],"they":[48],"often":[49],"overlook":[50],"challenges":[52,174],"posed":[53],"by":[54,117,144],"real-world":[55,124,316],"scenarios-where":[56],"data":[57,168,262],"is":[58],"collected":[59],"across":[60,164],"multiple":[61],"sessions":[62],"environments,":[64],"leading":[65],"to":[66,147,159,211,255],"significant":[67],"domain":[68],"shifts":[69],"heterogeneous":[71],"distributions.":[72],"Such":[73],"heterogeneity":[74],"can":[75],"result":[76],"catastrophic":[78,237],"forgetting":[79],"hinder":[81],"generalization":[83],"ability":[84,158],"of":[85,175,294],"conventional":[87],"models.":[88],"To":[89,170],"bridge":[90],"gap,":[92],"we":[93,177,240],"introduce":[94],"Continual":[96],"(CL-AVSR)":[100],"problem,":[101],"which":[102],"formulates":[103],"as":[105],"continual":[107,298],"learning":[108,183,299],"task.":[109],"We":[110],"establish":[111],"dedicated":[113],"benchmark":[114],"CL-AVSR":[116,287],"designing":[118],"three":[119],"experimental":[120],"scenarios":[121,153],"that":[122,247,273],"reflect":[123],"challenges:":[125],"introducing":[126],"varying":[127],"background":[128],"noise":[129],"audio":[132],"stream,":[133,140],"degrading":[134],"video":[135],"quality":[136],"dividing":[142],"tasks":[143],"speaker":[145],"characteristics":[146],"jointly":[148],"affect":[149],"modalities.":[151],"These":[152],"systematically":[154],"evaluate":[155],"model's":[157],"adapt":[160],"retain":[162],"knowledge":[163,205],"dynamic":[165],"non-stationary":[167],"streams.":[169],"address":[171],"unique":[173],"CL-AVSR,":[176],"propose":[178],"Interaction-enhanced":[180],"Multimodal":[181],"Prompt":[182],"(IMP)":[184],"framework.":[185],"IMP":[186,274,295],"builds":[187],"upon":[188],"pre-trained":[190],"AV-HuBERT":[191],"backbone":[192],"integrates":[194],"task-relevant":[195],"soft":[196],"prompts":[197,222,259],"with":[198,216],"cross-modal":[199],"cross-task":[201],"interactions,":[202],"enabling":[203],"efficient":[204],"transfer":[206],"high-quality":[208],"source":[209],"domains":[210,215],"typical":[212],"low-quality":[213],"target":[214],"minimal":[217],"parameter":[218],"overhead.":[219],"The":[220],"interactive":[221],"facilitate":[223],"fine-grained":[224],"alignment":[225],"adaptation":[227],"between":[228],"modalities":[229],"tasks,":[231],"while":[232],"contrastive":[233],"regularization":[234],"further":[235],"mitigates":[236],"forgetting.":[238],"Furthermore,":[239],"devise":[241],"multi-modal":[243,311],"prompt":[244],"selection":[245],"strategy":[246],"leverages":[248],"clustering-based":[249],"feature":[250],"analysis,":[251],"empowering":[252],"model":[254],"dynamically":[256],"select":[257],"optimal":[258],"unseen":[261],"distributions":[263],"during":[264],"inference.":[265],"Extensive":[266],"experiments":[267],"LRS2":[270],"dataset":[271],"demonstrate":[272],"achieves":[275],"substantial":[276],"improvements":[277],"over":[278],"strong":[279],"baselines,":[280],"setting":[281],"new":[282],"state-of-the-art":[283],"all":[286],"scenarios.":[288],"Our":[289],"results":[290],"highlight":[291],"effectiveness":[293],"enhancing":[297],"capabilities":[300],"AVSR,":[302],"paving":[303],"way":[305],"more":[307],"adaptable":[310],"recognition":[313],"systems":[314],"applications.":[317]},"counts_by_year":[],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2026-04-15T00:00:00"}