{"id":"https://openalex.org/W4408354440","doi":"https://doi.org/10.1109/icassp49660.2025.10890067","title":"DS-BTIAN: A Novel Deep-Shallow Bidirectional Transformer Interactive Attention Network for Multimodal Emotion Recognition","display_name":"DS-BTIAN: A Novel Deep-Shallow Bidirectional Transformer Interactive Attention Network for Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354440","doi":"https://doi.org/10.1109/icassp49660.2025.10890067"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890067","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/A5008377209","display_name":"Zengzhao Chen","orcid":"https://orcid.org/0000-0002-4022-9139"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zengzhao Chen","raw_affiliation_strings":["Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113921993","display_name":"Chuanxu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanxu Zhao","raw_affiliation_strings":["Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008033496","display_name":"Zhifeng Wang","orcid":"https://orcid.org/0000-0001-6960-509X"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Wang","raw_affiliation_strings":["Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320822","display_name":"Chuan Liu","orcid":"https://orcid.org/0000-0002-6362-0261"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Liu","raw_affiliation_strings":["Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004728094","display_name":"Qiuyu Zheng","orcid":"https://orcid.org/0000-0001-9778-8487"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyu Zheng","raw_affiliation_strings":["Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110751962","display_name":"Cheng Zou","orcid":"https://orcid.org/0009-0004-6934-612X"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zou","raw_affiliation_strings":["Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University,Faculty of Artificial Intelligence in Education,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008377209"],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":null,"apc_paid":null,"fwci":5.5828,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94624277,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9616000056266785,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9616000056266785,"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/computer-science","display_name":"Computer science","score":0.7209675908088684},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5763102769851685},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5758635997772217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46692726016044617},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42144089937210083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32684171199798584},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1272067129611969},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10147008299827576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209675908088684},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5763102769851685},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5758635997772217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46692726016044617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42144089937210083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32684171199798584},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1272067129611969},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10147008299827576},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890067","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323173","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2154091569","https://openalex.org/W2753840835","https://openalex.org/W3159124063","https://openalex.org/W3215440557","https://openalex.org/W4205964645","https://openalex.org/W4221162872","https://openalex.org/W4221162874","https://openalex.org/W4225635674","https://openalex.org/W4297841872","https://openalex.org/W4303649252","https://openalex.org/W4372260395","https://openalex.org/W4375869379","https://openalex.org/W4386158972","https://openalex.org/W4390414889","https://openalex.org/W4392904292","https://openalex.org/W4392910289","https://openalex.org/W4392910303","https://openalex.org/W4402111701","https://openalex.org/W4402112383","https://openalex.org/W4402112384","https://openalex.org/W6755207826","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2536562190","https://openalex.org/W2951359407","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,74],"propose":[4],"a":[5,94,131,149,194],"novel":[6,48],"Deep-Shallow":[7],"Bidirectional":[8],"Transformer":[9],"Interactive":[10],"Attention":[11],"Network":[12],"(DS-BTIAN)":[13],"designed":[14],"for":[15,27,34,179],"robust":[16],"multimodal":[17,71,172],"emotion":[18,81],"recognition.":[19],"DS-BTIAN":[20,125],"leverages":[21],"pre-trained":[22,177],"Wav2Vec2.0":[23],"and":[24,44,66,80,102,138,170],"BERT":[25],"models":[26,178],"efficient":[28],"feature":[29,108,180],"extraction":[30,181],"without":[31,182],"the":[32,62,118,145,159],"need":[33],"finetuning,":[35],"enhancing":[36,106],"representation":[37],"by":[38],"integrating":[39,171],"outputs":[40],"from":[41],"both":[42],"shallow":[43],"deep":[45],"layers.":[46],"A":[47],"bidirectional":[49],"cross-modal":[50],"interactive":[51],"attention":[52,57],"mechanism":[53],"based":[54],"on":[55,117,144],"multi-head":[56],"is":[58,91],"introduced,":[59],"adaptively":[60],"modeling":[61],"relationship":[63],"between":[64],"speech":[65,78],"text,":[67],"thus":[68],"promoting":[69],"effective":[70],"fusion.":[72],"Additionally,":[73],"incorporate":[75],"an":[76,139],"adaptive":[77],"segmentation":[79],"aggregation":[82],"strategy":[83,97],"to":[84],"better":[85],"capture":[86],"emotional":[87,173],"dynamics.":[88],"The":[89,121],"network":[90],"optimized":[92],"using":[93],"joint":[95],"training":[96],"combining":[98],"center":[99],"contrastive":[100],"loss":[101],"angular":[103],"Softmax":[104],"loss,":[105],"discriminative":[107],"learning.":[109],"We":[110],"conducted":[111],"extensive":[112],"speaker-independent":[113],"ten-fold":[114],"cross-validation":[115],"experiments":[116],"IEMOCAP":[119],"dataset.":[120],"results":[122],"demonstrate":[123],"that":[124],"significantly":[126],"outperforms":[127],"state-of-the-art":[128],"methods,":[129],"achieving":[130],"remarkable":[132],"average":[133],"weighted":[134],"accuracy":[135,141],"of":[136,142,161],"76.37%":[137],"unweighted":[140],"77.21%":[143],"test":[146],"set,":[147],"representing":[148],"substantial":[150],"improvement":[151],"over":[152],"baseline":[153],"models.":[154],"Ablation":[155],"studies":[156],"further":[157],"confirm":[158],"effectiveness":[160],"each":[162],"component,":[163],"underscoring":[164],"DS-BTIAN\u2019s":[165],"outstanding":[166],"capability":[167],"in":[168,199],"capturing":[169],"information.":[174],"By":[175],"utilizing":[176],"fine-tuning,":[183],"our":[184],"approach":[185],"not":[186],"only":[187],"delivers":[188],"superior":[189],"performance":[190],"but":[191],"also":[192],"offers":[193],"resource-efficient":[195],"solution,":[196],"particularly":[197],"valuable":[198],"scenarios":[200],"with":[201],"limited":[202],"computational":[203],"resources":[204],"or":[205],"annotated":[206],"data.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}