{"id":"https://openalex.org/W4408351984","doi":"https://doi.org/10.1109/icassp49660.2025.10890272","title":"DCIM-AVSR: Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module","display_name":"DCIM-AVSR: Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351984","doi":"https://doi.org/10.1109/icassp49660.2025.10890272"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5115695260","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0001-7549-2845"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075618349","display_name":"Haotian Jiang","orcid":"https://orcid.org/0000-0002-5952-7689"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Jiang","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071942824","display_name":"Haolin Huang","orcid":"https://orcid.org/0000-0002-2742-5055"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolin Huang","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036102162","display_name":"Yu Fang","orcid":"https://orcid.org/0000-0001-8664-4816"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Fang","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101343369","display_name":"Mengjie Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjie Xu","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391064","display_name":"Qian Wang","orcid":"https://orcid.org/0000-0002-4541-9898"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wang","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115695260"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":2.8781,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88629468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9909999966621399,"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/T11309","display_name":"Music and Audio Processing","score":0.9799000024795532,"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/dual","display_name":"Dual (grammatical number)","score":0.7324137687683105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6887630820274353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6713207364082336},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.47743329405784607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3671495318412781},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10067963600158691},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08129197359085083}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7324137687683105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6887630820274353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6713207364082336},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.47743329405784607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3671495318412781},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10067963600158691},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08129197359085083},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2194775991","https://openalex.org/W2594690981","https://openalex.org/W2890952074","https://openalex.org/W3015995734","https://openalex.org/W3097777922","https://openalex.org/W3116228589","https://openalex.org/W3162249256","https://openalex.org/W3162293946","https://openalex.org/W3197478142","https://openalex.org/W3197813307","https://openalex.org/W3205193540","https://openalex.org/W4224329471","https://openalex.org/W4297841641","https://openalex.org/W4319300051","https://openalex.org/W4372346152","https://openalex.org/W4375868974","https://openalex.org/W4385823066","https://openalex.org/W4392903670","https://openalex.org/W4392903825","https://openalex.org/W4392904168","https://openalex.org/W4392904484","https://openalex.org/W4392908934","https://openalex.org/W4392932002","https://openalex.org/W4393154934","https://openalex.org/W4401610131","https://openalex.org/W6754420807","https://openalex.org/W6780218876","https://openalex.org/W6810168380","https://openalex.org/W6847363464","https://openalex.org/W6847652939","https://openalex.org/W6870174606"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"Speech":[0,38],"recognition":[1],"is":[2,23],"the":[3,101,106,133,138,153],"technology":[4,22],"that":[5,99,122,131],"enables":[6],"machines":[7],"to":[8,135],"interpret":[9],"and":[10,33,57,86,143,161,168],"process":[11],"human":[12,77],"speech,":[13],"converting":[14],"spoken":[15],"language":[16],"into":[17,152],"text":[18],"or":[19],"commands.":[20],"This":[21,156],"essential":[24],"for":[25,171],"applications":[26],"such":[27],"as":[28],"virtual":[29],"assistants,":[30],"transcription":[31],"services,":[32],"communication":[34],"tools.":[35],"The":[36],"Audio-Visual":[37],"Recognition":[39],"(AVSR)":[40],"model":[41,98,124,154],"enhances":[42,158],"traditional":[43,61],"speech":[44],"recognition,":[45],"particularly":[46],"in":[47,164],"noisy":[48],"environments,":[49],"by":[50,126],"incorporating":[51],"visual":[52,144],"modalities":[53],"like":[54],"lip":[55],"movements":[56],"facial":[58],"expressions.":[59],"While":[60],"AVSR":[62,97,172],"models":[63,130],"trained":[64],"on":[65],"large-scale":[66],"datasets":[67],"with":[68,82],"numerous":[69],"parameters":[70,104],"can":[71],"achieve":[72],"remarkable":[73],"accuracy,":[74],"often":[75],"surpassing":[76],"performance,":[78,162],"they":[79],"also":[80],"come":[81],"high":[83],"training":[84],"costs":[85],"deployment":[87],"challenges.":[88],"To":[89],"address":[90],"these":[91],"issues,":[92],"we":[93,117],"introduce":[94],"an":[95],"efficient":[96],"reduces":[100],"number":[102],"of":[103,108],"through":[105],"integration":[107],"a":[109,119,165],"Dual":[110],"Conformer":[111],"Interaction":[112],"Module":[113],"(DCIM).":[114],"In":[115],"addition,":[116],"propose":[118],"pre-training":[120],"method":[121],"optimizes":[123],"performance":[125],"fine-tuning.":[127],"Unlike":[128],"conventional":[129],"require":[132],"system":[134],"independently":[136],"learn":[137],"hierarchical":[139],"relationship":[140],"between":[141],"audio":[142],"modalities,":[145],"our":[146],"approach":[147],"incorporates":[148],"this":[149],"distinction":[150],"directly":[151],"architecture.":[155],"design":[157],"both":[159],"efficiency":[160],"resulting":[163],"more":[166],"practical":[167],"effective":[169],"solution":[170],"tasks.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}