{"id":"https://openalex.org/W4416034152","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1018","title":"EMO-RL: Emotion-Rule-Based Reinforcement Learning Enhanced Audio-Language Model for Generalized Speech Emotion Recognition","display_name":"EMO-RL: Emotion-Rule-Based Reinforcement Learning Enhanced Audio-Language Model for Generalized Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034152","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1018"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1018","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1018","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1018.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1018.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101644250","display_name":"Pengcheng Li","orcid":"https://orcid.org/0009-0007-5302-9105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102832084","display_name":"Botao Zhao","orcid":"https://orcid.org/0000-0003-4399-4503"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Botao Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072654156","display_name":"Zuheng Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuheng Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064443099","display_name":"Junqing Peng","orcid":"https://orcid.org/0009-0009-2903-9615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junqing Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045696585","display_name":"Yayun He","orcid":"https://orcid.org/0000-0001-8202-3131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yayun He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","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":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18744","last_page":"18754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9402999877929688,"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":0.9402999877929688,"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":0.011900000274181366,"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":0.004900000058114529,"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/emotion-recognition","display_name":"Emotion recognition","score":0.3865000009536743},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.30480000376701355},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2904999852180481},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28200000524520874},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.27900001406669617},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.27469998598098755}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49639999866485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48080000281333923},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.45329999923706055},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555999994277954},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1018","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1018","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1018.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1018","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1018","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1018.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034152.pdf","grobid_xml":"https://content.openalex.org/works/W4416034152.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"Large":[1],"Audio-Language":[2],"Models":[3],"(LALMs)":[4],"have":[5,34],"exhibited":[6],"outstanding":[7],"performance":[8,13],"in":[9,14,19,30,37],"auditory":[10],"understanding,":[11],"their":[12],"affective":[15],"computing":[16],"scenarios,":[17],"particularly":[18],"emotion":[20,114],"recognition,":[21],"reasoning,":[22],"and":[23,66,99,139,142],"subtle":[24],"sentiment":[25],"differentiation,":[26],"remains":[27],"suboptimal.Recent":[28],"advances":[29],"Reinforcement":[31],"Learning":[32],"(RL)":[33],"shown":[35],"promise":[36],"improving":[38],"LALMs'":[39],"reasoning":[40,69,128],"abilities.However,":[41],"two":[42,92],"critical":[43],"challenges":[44],"hinder":[45],"the":[46,126,137,146],"direct":[47],"application":[48],"of":[49,130,149],"RL":[50],"techniques":[51],"to":[52],"Speech":[53],"Emotion":[54,95],"Recognition":[55],"(SER)":[56],"tasks:":[57],"(1)":[58],"convergence":[59],"instability":[60],"caused":[61],"by":[62],"ambiguous":[63],"emotional":[64,127],"boundaries":[65],"(2)":[67],"limited":[68],"ability":[70],"when":[71],"using":[72],"relatively":[73],"small":[74],"models":[75],"(e.g.,":[76],"7B-parameter":[77],"architectures).To":[78],"overcome":[79],"these":[80],"limitations,":[81],"we":[82],"introduce":[83],"EMO-RL,":[84],"a":[85],"novel":[86],"framework":[87],"incorporating":[88],"reinforcement":[89],"learning":[90],"with":[91,113],"key":[93],"innovations:":[94],"Similarity-Weighted":[96],"Reward":[97],"(ESWR)":[98],"Explicit":[100],"Structured":[101],"Reasoning":[102],"(ESR).Built":[103],"upon":[104],"pretrained":[105],"LALMs,":[106,131],"our":[107,119],"method":[108],"employs":[109],"group-relative":[110],"policy":[111],"optimization":[112],"constraints.Comprehensive":[115],"experiments":[116,144],"demonstrate":[117],"that":[118],"EMO-RL":[120],"training":[121],"strategies":[122],"can":[123],"significantly":[124],"enhance":[125],"capabilities":[129],"attaining":[132],"state-of-the-art":[133],"results":[134],"on":[135],"both":[136],"MELD":[138],"IEMOCAP":[140],"datasets,":[141],"cross-dataset":[143],"prove":[145],"strong":[147],"superiority":[148],"generalization.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}