{"id":"https://openalex.org/W7148534712","doi":"https://doi.org/10.1109/asru65441.2025.11434628","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","display_name":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148534712","doi":"https://doi.org/10.1109/asru65441.2025.11434628"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101838736","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab MoE Key Lab of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132790939","display_name":"Zhuo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["ByteDance Inc"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132820959","display_name":"Yuping Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["ByteDance Inc"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020559317","display_name":"E. Wei Chng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng-Siong Chng","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132816935","display_name":"Xie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab MoE Key Lab of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101838736"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85892711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.12600000202655792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.12600000202655792,"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":0.062199998646974564,"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/T12032","display_name":"Multisensory perception and integration","score":0.045899998396635056,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3294999897480011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.32170000672340393},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31369999051094055},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2944999933242798},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2831999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6528000235557556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47690001130104065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W3207553988","https://openalex.org/W4391021457","https://openalex.org/W4391021627","https://openalex.org/W4391021666","https://openalex.org/W4392902623","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4402112425","https://openalex.org/W4402671875","https://openalex.org/W4402684170","https://openalex.org/W4404784428","https://openalex.org/W4408352941","https://openalex.org/W4408355359","https://openalex.org/W4409362639","https://openalex.org/W4411119642","https://openalex.org/W4411119792","https://openalex.org/W4412945370"],"related_works":[],"abstract_inverted_index":{"Large":[0,160],"Audio-Language":[1],"Models":[2],"(LALMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"performance":[7,62,84],"in":[8,63,139],"tasks":[9,69,89],"involving":[10],"audio":[11,20],"perception":[12],"and":[13,19,67,73,87,117,128,149],"understanding,":[14],"such":[15],"as":[16],"speech":[17,74],"recognition":[18],"captioning.":[21],"However,":[22],"their":[23,49,61],"reasoning":[24,44,50,68,97,114,142],"capabilities-critical":[25],"for":[26,125,153],"solving":[27],"complex":[28],"real-world":[29],"problems-remain":[30],"underexplored.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,108],"conduct":[36],"the":[37,101,120,135],"first":[38],"exploration":[39],"into":[40,45],"integrating":[41],"Chain-of-Thought":[42],"(CoT)":[43],"LALMs":[46],"to":[47],"enhance":[48],"ability":[51],"across":[52,70],"auditory":[53],"modalities.":[54],"We":[55],"evaluate":[56],"representative":[57],"CoT":[58,80,138],"methods,":[59],"analyzing":[60],"both":[64],"information":[65],"extraction":[66],"sound,":[71],"music,":[72],"domains.":[75],"Our":[76],"findings":[77],"reveal":[78],"that":[79],"methods":[81],"significantly":[82],"improve":[83,105],"on":[85],"easy":[86],"medium":[88],"but":[90,144],"encounter":[91],"challenges":[92],"with":[93],"hard":[94],"tasks,":[95],"where":[96],"chains":[98],"can":[99],"confuse":[100],"model":[102],"rather":[103],"than":[104],"accuracy.":[106],"Additionally,":[107],"identify":[109],"a":[110],"positive":[111],"correlation":[112],"between":[113],"path":[115],"length":[116],"accuracy,":[118],"demonstrating":[119],"potential":[121],"of":[122,137],"scaling":[123],"inference":[124],"advanced":[126],"instruction-following":[127],"reasoning.":[129],"This":[130],"study":[131],"not":[132],"only":[133],"highlights":[134],"promise":[136],"enhancing":[140],"LALM":[141],"capabilities":[143],"also":[145],"identifies":[146],"key":[147],"limitations":[148],"provides":[150],"actionable":[151],"directions":[152],"future":[154],"research.":[155],"Index":[156],"Terms-Chain-of-Thought":[157],"(CoT),":[158],"Reasoning,":[159],"Audio":[161],"Language":[162],"Model":[163],"(LALM)":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}
