{"id":"https://openalex.org/W7138358946","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.62","title":"Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs","display_name":"Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7138358946","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.62"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.62","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.62.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.ijcnlp-long.62.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129732197","display_name":"Wenyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018641343","display_name":"Yunlei He","orcid":"https://orcid.org/0000-0003-2929-5554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingxu He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101339717","display_name":"Geyu Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geyu Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104978423","display_name":"Zhuohan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuohan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669804","display_name":"Shuo Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708477","display_name":"Bin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113268590","display_name":"Xunlong Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunlong Zou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705776","display_name":"Jeremy H. M. Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy H. M. Wong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991100","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0002-9903-0618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hardik Bhupendra Sailor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024798531","display_name":"Nancy Fang-Yih Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083501418","display_name":"AiTi Aw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"AiTi Aw","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"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":0.74660147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1132","last_page":"1148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7421000003814697,"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":0.7421000003814697,"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":0.10530000180006027,"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/T10860","display_name":"Speech and Audio Processing","score":0.04910000041127205,"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/task","display_name":"Task (project management)","score":0.3082999885082245},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.304500013589859},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.2987000048160553},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.28540000319480896},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2689000070095062}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4828999936580658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47429999709129333},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.ijcnlp-long.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.62","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.62.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.62","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.62.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138358946.pdf","grobid_xml":"https://content.openalex.org/works/W7138358946.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Wenyu":[0],"Zhang,":[1],"Yingxu":[2],"He,":[3],"Geyu":[4],"Lin,":[5],"Zhuohan":[6],"Liu,":[7],"Shuo":[8],"Sun,":[9],"Bin":[10],"Wang,":[11,19],"Xunlong":[12],"Zou,":[13],"Jeremy":[14],"H.":[15],"M.":[16],"Wong,":[17],"Qiongqiong":[18],"Hardik":[20],"Bhupendra":[21],"Sailor,":[22],"Nancy":[23],"F.":[24],"Chen,":[25],"AiTi":[26],"Aw.":[27],"Proceedings":[28],"of":[29,43,47],"the":[30,40,44,48],"14th":[31],"International":[32],"Joint":[33],"Conference":[34,42],"on":[35],"Natural":[36],"Language":[37],"Processing":[38],"and":[39],"4th":[41],"Asia-Pacific":[45],"Chapter":[46],"Association":[49],"for":[50],"Computational":[51],"Linguistics.":[52],"2025.":[53]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}
