{"id":"https://openalex.org/W4410636336","doi":"https://doi.org/10.1145/3701716.3717561","title":"Exploring Multimodal Pre-trained Models for Speech Emotion Recognition","display_name":"Exploring Multimodal Pre-trained Models for Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636336","doi":"https://doi.org/10.1145/3701716.3717561"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717561","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717561","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717561","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717561","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhiyu Liu","orcid":"https://orcid.org/0009-0006-3578-2649"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiyu Liu","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-3578-2649","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012498345","display_name":"Junchen Fu","orcid":"https://orcid.org/0000-0003-4759-2042"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junchen Fu","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4759-2042","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaiwen Zheng","orcid":"https://orcid.org/0009-0007-2516-8407"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kaiwen Zheng","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0007-2516-8407","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9228-1759","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10206933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2176","last_page":"2180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958000183105469,"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":0.9957000017166138,"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/speech-recognition","display_name":"Speech recognition","score":0.7534024715423584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7358806133270264},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6394177079200745},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4478939473628998},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4331076443195343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41292911767959595}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7534024715423584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358806133270264},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6394177079200745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4478939473628998},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4331076443195343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41292911767959595}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3701716.3717561","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717561","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717561","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:352097","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/view/author/73116.html>,","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:eprints.gla.ac.uk:352097","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/79515.html>,","pdf_url":"https://eprints.gla.ac.uk/352097/2/352097.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717561","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717561","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717561","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636336.pdf","grobid_xml":"https://content.openalex.org/works/W4410636336.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W4220959373","https://openalex.org/W4309564859","https://openalex.org/W4317380951","https://openalex.org/W4378465281","https://openalex.org/W4393942911","https://openalex.org/W4401307507","https://openalex.org/W6603827241","https://openalex.org/W6604190760","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W3151937861","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Multimodal":[0],"pre-trained":[1],"models":[2,36],"have":[3],"demonstrated":[4],"remarkable":[5],"capabilities":[6],"in":[7],"processing":[8],"diverse":[9],"data":[10],"types,":[11],"including":[12],"text":[13],"and":[14,40,66,85,102],"audio.":[15],"However,":[16],"their":[17,76],"potential":[18],"for":[19,37,46,105],"Speech":[20],"Emotion":[21],"Recognition":[22],"(SER)":[23],"remains":[24],"relatively":[25],"underexplored.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"investigate":[31],"the":[32,42,88],"effectiveness":[33,84],"of":[34],"such":[35],"SER":[38],"tasks":[39],"evaluate":[41],"state-of-the-art":[43],"IISAN":[44,52,80],"framework":[45],"efficient":[47],"fine-tuning.":[48],"We":[49],"further":[50],"improved":[51],"by":[53],"incorporating":[54],"a":[55,99],"dynamic":[56],"gating":[57],"mechanism,":[58,97],"referred":[59],"to":[60,63],"as":[61],"IISAN-MOE,":[62],"enhance":[64],"adaptability":[65],"performance.":[67],"Experimental":[68],"results":[69],"confirm":[70],"that":[71],"multimodal":[72,106],"approaches":[73],"consistently":[74],"outperform":[75],"single-modal":[77],"counterparts,":[78],"with":[79],"significantly":[81],"boosting":[82],"both":[83],"efficiency.":[86],"Moreover,":[87],"newly":[89],"proposed":[90],"IISAN-MOE":[91],"refines":[92],"IISAN's":[93],"original":[94],"static":[95],"fusion":[96],"offering":[98],"more":[100],"flexible":[101],"advanced":[103],"solution":[104],"speech":[107],"emotion":[108],"recognition.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}