{"id":"https://openalex.org/W7166703274","doi":"https://doi.org/10.7148/2026-0676","title":"Exploring transfer learning for speech emotion recognition in italian","display_name":"Exploring transfer learning for speech emotion recognition in italian","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7166703274","doi":"https://doi.org/10.7148/2026-0676"},"language":null,"primary_location":{"id":"doi:10.7148/2026-0676","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0676","pdf_url":"https://doi.org/10.7148/2026-0676","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7148/2026-0676","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019857437","display_name":"Salvatore Serrano","orcid":"https://orcid.org/0000-0003-0507-5186"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Serrano","raw_affiliation_strings":["Department of Engineering , University of Messina , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina , Italy","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079839964","display_name":"Marica Amadeo","orcid":"https://orcid.org/0000-0003-2370-5145"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marica Amadeo","raw_affiliation_strings":["Department of Engineering , University of Messina , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina , Italy","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033292026","display_name":"Marco Scarpa","orcid":"https://orcid.org/0000-0002-9560-7504"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Lucio Scarpa","raw_affiliation_strings":["Department of Engineering , University of Messina , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina , Italy","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015344591","display_name":"Salvatore Spinella","orcid":"https://orcid.org/0000-0002-1541-0083"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Spinella","raw_affiliation_strings":["Department of Engineering , University of Messina , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina , Italy","institution_ids":["https://openalex.org/I112862951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I112862951"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"676","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9797999858856201,"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":0.9797999858856201,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.005100000184029341,"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":0.004600000102072954,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.657800018787384},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5770000219345093},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5529999732971191},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.424699991941452},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4147000014781952},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.37040001153945923}],"concepts":[{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6226999759674072},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5770000219345093},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5529999732971191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.515500009059906},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3573000133037567},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26420000195503235},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2026-0676","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0676","pdf_url":"https://doi.org/10.7148/2026-0676","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.7148/2026-0676","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0676","pdf_url":"https://doi.org/10.7148/2026-0676","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5317426919937134,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166703274.pdf","grobid_xml":"https://content.openalex.org/works/W7166703274.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"has":[4],"achieved":[5],"significant":[6,116],"progress":[7],"in":[8,70,120],"widely":[9],"studied":[10],"languages":[11],"such":[12],"as":[13],"English,":[14],"driven":[15],"by":[16,81],"the":[17,31,124,141],"availability":[18],"of":[19,33,127],"large-scale":[20],"benchmark":[21],"datasets.":[22],"However,":[23,115],"research":[24],"on":[25,55,60],"Italian":[26,49,63,153],"remains":[27],"limited":[28],"due":[29],"to":[30,94,97],"scarcity":[32],"recent":[34,62],"and":[35,74,79,90,107,113],"complementary":[36,66],"emotional":[37],"speech":[38],"corpora.":[39],"This":[40],"paper":[41],"investigates":[42],"a":[43],"feature-based":[44],"transfer":[45,149],"learning":[46,150],"approach":[47],"for":[48,152],"SER":[50,154],"using":[51],"audio":[52],"models":[53,109],"pre-trained":[54],"AudioSet.":[56],"Experiments":[57],"are":[58],"conducted":[59],"two":[61],"corpora":[64],"with":[65],"characteristics:":[67],"AI4SER,":[68],"recorded":[69],"controlled":[71],"laboratory":[72],"conditions,":[73],"Emozionalmente,":[75],"developed":[76],"through":[77],"crowdsourcing":[78],"characterized":[80],"higher":[82],"acoustic":[83],"variability.":[84],"A":[85],"three-scenario":[86],"evaluation":[87],"protocol\u2014within-corpus,":[88],"cross-corpus,":[89],"joint":[91],"training\u2014is":[92],"adopted":[93],"assess":[95],"robustness":[96],"domain":[98],"shift.":[99],"Results":[100],"indicate":[101],"that":[102],"embeddings":[103],"extracted":[104],"from":[105],"deeper":[106],"higher-capacity":[108],"consistently":[110],"improve":[111],"performance":[112],"robustness.":[114],"degradation":[117],"is":[118],"observed":[119],"cross-corpus":[121],"settings,":[122],"highlighting":[123],"strong":[125],"impact":[126],"dataset-specific":[128],"characteristics.":[129],"Joint":[130],"training":[131],"partially":[132],"mitigates":[133],"this":[134],"effect":[135],"but":[136],"does":[137],"not":[138],"fully":[139],"eliminate":[140],"generalization":[142],"gap.":[143],"These":[144],"findings":[145],"provide":[146],"insights":[147],"into":[148],"effectiveness":[151],"under":[155],"heterogeneous":[156],"recording":[157],"conditions.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-01T00:00:00"}