{"id":"https://openalex.org/W4415433375","doi":"https://doi.org/10.21437/interspeech.2025-1357","title":"Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild","display_name":"Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433375","doi":"https://doi.org/10.21437/interspeech.2025-1357"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1357","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.07282","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113145213","display_name":"Jing-Tong Tzeng","orcid":"https://orcid.org/0000-0002-2053-0581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing-Tong Tzeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026257400","display_name":"Bo-Hao Su","orcid":"https://orcid.org/0009-0001-0912-7417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo-Hao Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072913376","display_name":"Ya-Tse Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya-Tse Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111952284","display_name":"Hsing-Hang Chou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsing-Hang Chou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26011884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4708","last_page":"4712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5508000254631042,"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":0.5508000254631042,"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/T12031","display_name":"Speech and dialogue systems","score":0.49470001459121704,"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/valence","display_name":"Valence (chemistry)","score":0.7940999865531921},{"id":"https://openalex.org/keywords/emotional-valence","display_name":"Emotional valence","score":0.6212000250816345},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.536300003528595},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45159998536109924},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.7940999865531921},{"id":"https://openalex.org/C3020774634","wikidata":"https://www.wikidata.org/wiki/Q3113318","display_name":"Emotional valence","level":3,"score":0.6212000250816345},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4860000014305115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45500001311302185},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4034999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4027999937534332},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2597000002861023}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1357","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.07282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07282","pdf_url":"https://arxiv.org/pdf/2508.07282","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.07282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07282","pdf_url":"https://arxiv.org/pdf/2508.07282","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,19],"revisit":[4],"key":[5],"training":[6,87],"strategies":[7],"in":[8,13,34,66,78],"machine":[9],"learning":[10],"often":[11],"overlooked":[12],"favor":[14],"of":[15,60],"deeper":[16],"architectures.":[17],"Specifically,":[18],"explore":[20],"balancing":[21],"strategies,":[22],"activation":[23,100],"functions,":[24],"and":[25,75,99],"fine-tuning":[26,73],"techniques":[27],"to":[28,120],"enhance":[29,103],"speech":[30],"emotion":[31],"recognition":[32],"(SER)":[33],"naturalistic":[35],"conditions.":[36],"Our":[37,49],"findings":[38],"show":[39],"that":[40,111],"simple":[41],"modifications":[42],"improve":[43],"generalization":[44],"with":[45],"minimal":[46],"architectural":[47],"changes.":[48],"multi-modal":[50],"fusion":[51,85],"model,":[52],"integrating":[53],"these":[54],"optimizations,":[55],"achieves":[56],"a":[57,79],"valence":[58,64,94],"CCC":[59],"0.6953,":[61],"the":[62,88,92],"best":[63],"score":[65],"Task":[67],"2:":[68],"Emotional":[69],"Attribute":[70],"Regression.":[71],"Notably,":[72],"RoBERTa":[74],"WavLM":[76],"separately":[77],"single-modality":[80],"setting,":[81],"followed":[82],"by":[83],"feature":[84],"without":[86,105],"backbone":[89],"extractor,":[90],"yields":[91],"highest":[93],"performance.":[95],"Additionally,":[96],"focal":[97],"loss":[98],"functions":[101],"significantly":[102],"performance":[104],"increasing":[106],"complexity.":[107],"These":[108],"results":[109],"suggest":[110],"refining":[112],"core":[113],"components,":[114],"rather":[115],"than":[116],"deepening":[117],"models,":[118],"leads":[119],"more":[121],"robust":[122],"SER":[123],"in-the-wild.":[124]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-23T00:00:00"}