{"id":"https://openalex.org/W4401890484","doi":"https://doi.org/10.3390/s24175506","title":"MelTrans: Mel-Spectrogram Relationship-Learning for Speech Emotion Recognition via Transformers","display_name":"MelTrans: Mel-Spectrogram Relationship-Learning for Speech Emotion Recognition via Transformers","publication_year":2024,"publication_date":"2024-08-25","ids":{"openalex":"https://openalex.org/W4401890484","doi":"https://doi.org/10.3390/s24175506","pmid":"https://pubmed.ncbi.nlm.nih.gov/39275417"},"language":"en","primary_location":{"id":"doi:10.3390/s24175506","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24175506","pdf_url":"https://www.mdpi.com/1424-8220/24/17/5506/pdf?version=1724656101","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/17/5506/pdf?version=1724656101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100629689","display_name":"Hui Li","orcid":"https://orcid.org/0000-0002-1595-9113"},"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"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China","institution_ids":["https://openalex.org/I40963666"]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331436","display_name":"Jiawen Li","orcid":"https://orcid.org/0000-0001-9339-2557"},"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":"Jiawen Li","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697640","display_name":"Hai Liu","orcid":"https://orcid.org/0000-0003-2758-1100"},"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":"Hai Liu","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089292643","display_name":"Tingting Liu","orcid":"https://orcid.org/0000-0003-0348-949X"},"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":"Tingting Liu","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110018131","display_name":"Qiang Chen","orcid":"https://orcid.org/0009-0000-9078-1602"},"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":"Qiang Chen","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008826095","display_name":"Xinge You","orcid":"https://orcid.org/0000-0002-6227-1346"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinge You","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089292643"],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":8.1246,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9789058,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"24","issue":"17","first_page":"5506","last_page":"5506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.9975000023841858,"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/spectrogram","display_name":"Spectrogram","score":0.7351513504981995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6821200251579285},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6526594161987305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5274781584739685},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44815385341644287},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4420815408229828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3799172341823578},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35937511920928955},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12948578596115112}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7351513504981995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821200251579285},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6526594161987305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5274781584739685},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44815385341644287},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4420815408229828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799172341823578},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35937511920928955},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12948578596115112},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"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":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"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":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","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":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","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":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s24175506","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24175506","pdf_url":"https://www.mdpi.com/1424-8220/24/17/5506/pdf?version=1724656101","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:39275417","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39275417","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11398065","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11398065","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11398065/pdf/sensors-24-05506.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:ffe6e7bbe5dd4c90817c737335c22e7e","is_oa":true,"landing_page_url":"https://doaj.org/article/ffe6e7bbe5dd4c90817c737335c22e7e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 24, Iss 17, p 5506 (2024)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/24/17/5506/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s24175506","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s24175506","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24175506","pdf_url":"https://www.mdpi.com/1424-8220/24/17/5506/pdf?version=1724656101","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401890484.pdf","grobid_xml":"https://content.openalex.org/works/W4401890484.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W79136065","https://openalex.org/W175750906","https://openalex.org/W1599928937","https://openalex.org/W2043152858","https://openalex.org/W2146334809","https://openalex.org/W2161372178","https://openalex.org/W2168465881","https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2752782242","https://openalex.org/W2924116307","https://openalex.org/W2983165789","https://openalex.org/W2990825125","https://openalex.org/W3007946940","https://openalex.org/W3047375952","https://openalex.org/W3095648847","https://openalex.org/W3098571047","https://openalex.org/W3182657421","https://openalex.org/W3196508562","https://openalex.org/W3196735225","https://openalex.org/W3197438177","https://openalex.org/W3203925315","https://openalex.org/W3209572141","https://openalex.org/W3215440557","https://openalex.org/W4210777104","https://openalex.org/W4214913438","https://openalex.org/W4221162872","https://openalex.org/W4225776299","https://openalex.org/W4289516314","https://openalex.org/W4289524424","https://openalex.org/W4303649252","https://openalex.org/W4312313987","https://openalex.org/W4312402009","https://openalex.org/W4313887688","https://openalex.org/W4316035551","https://openalex.org/W4321609205","https://openalex.org/W4361994820","https://openalex.org/W4366967249","https://openalex.org/W4367172564","https://openalex.org/W4367281761","https://openalex.org/W4379033883","https://openalex.org/W4386397728","https://openalex.org/W4388240351","https://openalex.org/W4391620705","https://openalex.org/W4392903514","https://openalex.org/W4392904414","https://openalex.org/W4393193328","https://openalex.org/W6684552223"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"(SER)":[3],"is":[4,60,82],"not":[5],"only":[6],"a":[7,15,54,83,101,143],"ubiquitous":[8],"aspect":[9],"of":[10,21,40,79,104,125,149,158],"everyday":[11],"communication,":[12],"but":[13],"also":[14],"central":[16],"focus":[17],"in":[18,31,44,108,139,162],"the":[19,37,77,87,115,123,147,156,159,164],"field":[20],"human-computer":[22],"interaction.":[23],"However,":[24],"SER":[25,169],"faces":[26],"several":[27],"challenges,":[28,51],"including":[29],"difficulties":[30],"detecting":[32],"subtle":[33],"emotional":[34,105],"nuances":[35],"and":[36,73,118,136],"complicated":[38],"task":[39],"recognizing":[41],"speech":[42,67,98,109,140],"emotions":[43],"noisy":[45],"environments.":[46],"To":[47],"effectively":[48],"address":[49],"these":[50,150],"we":[52],"introduce":[53],"Transformer-based":[55],"model":[56,161],"called":[57],"MelTrans,":[58],"which":[59],"designed":[61],"to":[62,132],"distill":[63],"critical":[64,134],"clues":[65],"from":[66],"data":[68],"by":[69,168],"learning":[70],"core":[71],"features":[72],"long-range":[74,137],"dependencies.":[75],"At":[76],"heart":[78],"our":[80],"approach":[81],"dual-stream":[84],"framework.":[85],"Using":[86],"Transformer":[88],"architecture":[89],"as":[90],"its":[91],"foundation,":[92],"MelTrans":[93],"deciphers":[94],"broad":[95],"dependencies":[96,138],"within":[97,146],"mel-spectrograms,":[99],"facilitating":[100],"nuanced":[102],"understanding":[103],"cues":[106,135],"embedded":[107],"signals.":[110],"Comprehensive":[111],"experimental":[112],"evaluations":[113],"on":[114],"EmoDB":[116],"(92.52%)":[117],"IEMOCAP":[119],"(76.54%)":[120],"datasets":[121],"demonstrate":[122],"effectiveness":[124,157],"MelTrans.":[126],"These":[127,153],"results":[128,154],"highlight":[129,155],"MelTrans's":[130],"ability":[131],"capture":[133],"data,":[141],"setting":[142],"new":[144],"benchmark":[145],"context":[148],"specific":[151],"datasets.":[152],"proposed":[160],"addressing":[163],"complex":[165],"challenges":[166],"posed":[167],"tasks.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
