{"id":"https://openalex.org/W4415428937","doi":"https://doi.org/10.3233/faia250823","title":"Explainable Multimodal Hybrid Vision Transformers for Emotional Speech Recognition","display_name":"Explainable Multimodal Hybrid Vision Transformers for Emotional Speech Recognition","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428937","doi":"https://doi.org/10.3233/faia250823"},"language":null,"primary_location":{"id":"doi:10.3233/faia250823","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250823","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250823","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088987855","display_name":"Pawe\u0142 Powro\u017anik","orcid":"https://orcid.org/0000-0002-5705-4785"},"institutions":[{"id":"https://openalex.org/I8264552","display_name":"Lublin University of Technology","ror":"https://ror.org/024zjzd49","country_code":"PL","type":"education","lineage":["https://openalex.org/I8264552"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Pawel Powroznik","raw_affiliation_strings":["Department of Computer Science, Lublin University of Technology"],"raw_orcid":"https://orcid.org/0000-0002-5705-4785","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lublin University of Technology","institution_ids":["https://openalex.org/I8264552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089968607","display_name":"Maria Skublewska\u2010Paszkowska","orcid":"https://orcid.org/0000-0002-0760-7126"},"institutions":[{"id":"https://openalex.org/I8264552","display_name":"Lublin University of Technology","ror":"https://ror.org/024zjzd49","country_code":"PL","type":"education","lineage":["https://openalex.org/I8264552"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Maria Skublewska-Paszkowska","raw_affiliation_strings":["Department of Computer Science, Lublin University of Technology"],"raw_orcid":"https://orcid.org/0000-0002-0760-7126","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lublin University of Technology","institution_ids":["https://openalex.org/I8264552"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krzysztof Dziedzic","orcid":"https://orcid.org/0009-0007-3458-5464"},"institutions":[{"id":"https://openalex.org/I8264552","display_name":"Lublin University of Technology","ror":"https://ror.org/024zjzd49","country_code":"PL","type":"education","lineage":["https://openalex.org/I8264552"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Krzysztof Dziedzic","raw_affiliation_strings":["Department of Computer Science, Lublin University of Technology"],"raw_orcid":"https://orcid.org/0009-0007-3458-5464","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lublin University of Technology","institution_ids":["https://openalex.org/I8264552"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marcin Barszcz","orcid":"https://orcid.org/0000-0003-4909-9980"},"institutions":[{"id":"https://openalex.org/I8264552","display_name":"Lublin University of Technology","ror":"https://ror.org/024zjzd49","country_code":"PL","type":"education","lineage":["https://openalex.org/I8264552"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Marcin Barszcz","raw_affiliation_strings":["Department of Computer Science, Lublin University of Technology"],"raw_orcid":"https://orcid.org/0000-0003-4909-9980","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lublin University of Technology","institution_ids":["https://openalex.org/I8264552"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kinga Chwaleba","orcid":"https://orcid.org/0000-0002-9061-4414"},"institutions":[{"id":"https://openalex.org/I8264552","display_name":"Lublin University of Technology","ror":"https://ror.org/024zjzd49","country_code":"PL","type":"education","lineage":["https://openalex.org/I8264552"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Kinga Chwaleba","raw_affiliation_strings":["Department of Computer Science, Lublin University of Technology"],"raw_orcid":"https://orcid.org/0000-0002-9061-4414","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lublin University of Technology","institution_ids":["https://openalex.org/I8264552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107665040","display_name":"Weronika Wach","orcid":"https://orcid.org/0009-0004-6164-5862"},"institutions":[{"id":"https://openalex.org/I8264552","display_name":"Lublin University of Technology","ror":"https://ror.org/024zjzd49","country_code":"PL","type":"education","lineage":["https://openalex.org/I8264552"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Weronika Wach","raw_affiliation_strings":["Department of Computer Science, Lublin University of Technology"],"raw_orcid":"https://orcid.org/0009-0004-6164-5862","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lublin University of Technology","institution_ids":["https://openalex.org/I8264552"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026255242","display_name":"Vimala Nunavath","orcid":"https://orcid.org/0000-0001-6911-8056"},"institutions":[{"id":"https://openalex.org/I2801380234","display_name":"University of South-Eastern Norway","ror":"https://ror.org/05ecg5h20","country_code":"NO","type":"education","lineage":["https://openalex.org/I2801380234"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Vimala Nunavath","raw_affiliation_strings":["Department of Science and Industry systems, University of South-Eastern Norway"],"raw_orcid":"https://orcid.org/0000-0001-6911-8056","affiliations":[{"raw_affiliation_string":"Department of Science and Industry systems, University of South-Eastern Norway","institution_ids":["https://openalex.org/I2801380234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5088987855"],"corresponding_institution_ids":["https://openalex.org/I8264552"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4785394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8754000067710876,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8754000067710876,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6693999767303467},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4343000054359436},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.38920000195503235},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.37929999828338623},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3758000135421753},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3709000051021576},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178999781608582},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6693999767303467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5855000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524399995803833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.38920000195503235},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.2547999918460846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2517000138759613},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250823","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250823","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250823","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250823","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"speech":[1,113,144],"possesses":[2],"a":[3,64,87,107],"great":[4],"variety":[5],"of":[6,10,46,142],"conveying":[7],"information.":[8],"Identification":[9],"the":[11,134,146,187],"transmitted":[12],"emotions":[13,33],"is":[14,27,93],"crucial":[15],"for":[16,40,52],"effective":[17],"communication,":[18],"social,":[19],"and":[20,82,123,152,164,196],"human-computer":[21],"interactions.":[22],"Developing":[23],"an":[24,97],"efficient":[25],"model":[26,159,188],"demanding":[28],"issue":[29],"due":[30],"to":[31,96],"subtle":[32],"differences,":[34],"subjective":[35],"assessment":[36],"or":[37],"sound":[38],"characteristics":[39],"specific":[41],"language.":[42],"A":[43,115],"wide":[44],"range":[45],"deep":[47],"learning":[48],"methods":[49],"are":[50],"developed":[51],"this":[53],"challenging":[54],"task.":[55],"We":[56,132],"present":[57],"Explainable":[58],"Multimodal":[59],"Hybrid":[60],"Vision":[61,109],"Transformers":[62],"(EM-H-ViT),":[63],"unified":[65],"framework":[66],"that":[67,171,186],"fuses":[68],"four":[69,137],"orthogonal":[70],"feature":[71],"spaces:":[72],"Fuzzy-Transform":[73],"energy":[74],"maps,":[75,128],"discrete":[76],"Wavelet":[77],"coefficients,":[78,85],"complex":[79],"Fourier":[80],"spectrograms,":[81],"Mel":[83],"spectrum":[84],"within":[86],"lightweight":[88],"CNN\u2013ViT":[89],"backbone.":[90],"Each":[91],"modality":[92],"first":[94],"projected":[95],"image-like":[98],"tensor.":[99],"Modality-specific":[100],"convolutional":[101],"branches":[102],"capture":[103],"local":[104],"patterns,":[105],"while":[106],"shared":[108],"Transformer":[110],"aggregates":[111],"long-range":[112],"context.":[114],"cross-modal":[116],"attention":[117],"gate":[118],"learns":[119],"data-driven":[120],"fusion":[121],"weights":[122],"simultaneously":[124],"produces":[125],"pixel-level":[126],"saliency":[127],"enabling":[129],"post-hoc":[130],"interpretation.":[131],"evaluate":[133],"EM-H-ViT":[135],"on":[136],"benchmark":[138],"corpora":[139],"containing":[140],"recordings":[141],"emotional":[143],"in":[145],"following":[147],"languages:":[148],"Polish,":[149],"English,":[150],"German":[151],"Danish,":[153],"using":[154],"speaker-independent":[155],"splits.":[156],"The":[157],"proposed":[158],"reaches":[160],"95.2%,":[161],"98.7%,":[162],"97.6%,":[163],"95.1%":[165],"accuracy,":[166],"respectively.":[167],"Ablation":[168],"studies":[169],"show":[170],"removing":[172],"any":[173],"single":[174],"transform":[175],"degrades":[176],"performance":[177],"by":[178],"3.4%-6.8%,":[179],"confirming":[180],"their":[181],"complementarity.":[182],"Obtained":[183],"results":[184],"demonstrate":[185],"can":[189],"deliver,":[190],"language":[191],"independent,":[192],"both":[193],"superior":[194],"accuracy":[195],"transparent":[197],"reasoning.":[198]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}