{"id":"https://openalex.org/W7151308413","doi":"https://doi.org/10.1016/j.eswa.2026.132369","title":"DAP-Whisper: A robust audio-visual speech recognition system via distribution-aware prompting and consistency-gated modulation","display_name":"DAP-Whisper: A robust audio-visual speech recognition system via distribution-aware prompting and consistency-gated modulation","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151308413","doi":"https://doi.org/10.1016/j.eswa.2026.132369"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.132369","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132369","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-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/A5133131604","display_name":"Xinyue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China"],"raw_orcid":"https://orcid.org/0009-0003-4094-492X","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133131933","display_name":"Yakun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yakun Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China"],"raw_orcid":"https://orcid.org/0000-0001-5829-1371","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133069156","display_name":"Xingyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China"],"raw_orcid":"https://orcid.org/0000-0003-0783-684X","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086000146","display_name":"Changyan Zheng","orcid":"https://orcid.org/0000-0002-2088-9308"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyan Zheng","raw_affiliation_strings":["Northwestern Polytechnical University, Xi\u2019an Shaanxi, 710072, China"],"raw_orcid":"https://orcid.org/0000-0002-2088-9308","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi\u2019an Shaanxi, 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133083666","display_name":"Tao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yu","raw_affiliation_strings":["Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","University of Electronic Science and Technology of China, Chengdu Sichuan, 611731, China"],"raw_orcid":"https://orcid.org/0009-0007-0567-1857","affiliations":[{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu Sichuan, 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133129708","display_name":"Liang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xie","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China"],"raw_orcid":"https://orcid.org/0000-0002-8286-6785","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiangbin Zheng","orcid":"https://orcid.org/0009-0004-2936-2870"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangbin Zheng","raw_affiliation_strings":["Northwestern Polytechnical University, Xi\u2019an Shaanxi, 710072, China"],"raw_orcid":"https://orcid.org/0009-0004-2936-2870","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi\u2019an Shaanxi, 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133114927","display_name":"Erwei Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erwei Yin","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China"],"raw_orcid":"https://orcid.org/0000-0002-2147-9888","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, Beijing, 100071, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5133131933"],"corresponding_institution_ids":["https://openalex.org/I2802541053","https://openalex.org/I4210100255"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35942029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"322","issue":null,"first_page":"132369","last_page":"132369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8783000111579895,"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":0.8783000111579895,"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":0.08060000091791153,"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":0.008999999612569809,"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/modulation","display_name":"Modulation (music)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.40149998664855957},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.36489999294281006},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33629998564720154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32100000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782800018787384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6998999714851379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36489999294281006},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.eswa.2026.132369","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132369","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5741074483","display_name":null,"funder_award_id":"2023YFF1203903","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5799476605","display_name":null,"funder_award_id":"2023YFF1203900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5931773243","display_name":null,"funder_award_id":"62332019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6231997530","display_name":null,"funder_award_id":"20240484513","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2890952074","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4220829848","https://openalex.org/W4396768628","https://openalex.org/W4397039346","https://openalex.org/W4402112360","https://openalex.org/W4407273819","https://openalex.org/W4410153306","https://openalex.org/W7106232458","https://openalex.org/W7148436364"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-04-08T00:00:00"}
