{"id":"https://openalex.org/W7166859166","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1776","title":"Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding","display_name":"Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166859166","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1776"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1776","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1776","pdf_url":"https://aclanthology.org/2026.findings-acl.1776.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1776.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139775892","display_name":"Jieyi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jieyi Wang","raw_affiliation_strings":["Peking University ,","Shanghai AI Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]},{"raw_affiliation_string":"Shanghai AI Laboratory ,","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786716","display_name":"Yazhe Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I1338034494","display_name":"XLAB (Slovenia)","ror":"https://ror.org/04xa5qt51","country_code":"SI","type":"company","lineage":["https://openalex.org/I1338034494"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK","SI"],"is_corresponding":false,"raw_author_name":"Yazhe Niu","raw_affiliation_strings":["CUHK MMLab ,","Shanghai AI Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK MMLab ,","institution_ids":["https://openalex.org/I1338034494","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Shanghai AI Laboratory ,","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139821318","display_name":"Dexuan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dexuan Xu","raw_affiliation_strings":["Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139791679","display_name":"Zhongyu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyu Wei","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.1002,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98751445,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"35653","last_page":"35671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11649999767541885,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11649999767541885,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.11309999972581863,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.08760000020265579,"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/process","display_name":"Process (computing)","score":0.33480000495910645},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.2574999928474426},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2542000114917755},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2535000145435333},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24420000612735748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24310000240802765},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.24230000376701355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1776","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1776","pdf_url":"https://aclanthology.org/2026.findings-acl.1776.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1776","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1776","pdf_url":"https://aclanthology.org/2026.findings-acl.1776.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320325413","display_name":"Shanghai Municipal Commission of Economy and Informatization","ror":"https://ror.org/04166ws88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166859166.pdf","grobid_xml":"https://content.openalex.org/works/W7166859166.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"Large":[1],"Audio":[2],"Language":[3],"Models":[4],"have":[5],"demonstrated":[6],"impressive":[7],"capabilities":[8],"in":[9,30,90],"audio":[10,20,157],"understanding.However,":[11],"they":[12],"often":[13],"suffer":[14],"from":[15,55],"perceptual":[16,64,118],"errors,":[17],"while":[18],"reliable":[19],"reasoning":[21,65,123,152],"is":[22],"unattainable":[23],"without":[24],"first":[25,39],"grounding":[26],"the":[27,82,100,137,147],"model's":[28,101],"perception":[29],"structured":[31],"auditory":[32],"scenes.Inspired":[33],"by":[34],"Auditory":[35],"Scene":[36],"Analysis,":[37],"we":[38,70,80,95],"introduce":[40,105],"a":[41,48,73],"Perception-Aware":[42],"Question":[43],"Answering":[44],"(PAQA)":[45],"dataset.PAQA":[46],"implements":[47],"hierarchical":[49],"decoupling":[50],"strategy":[51],"that":[52,131],"separates":[53],"speech":[54],"environmental":[56],"sound":[57],"and":[58,116,155],"distinguishes":[59],"multiple":[60],"speakers,":[61],"providing":[62],"explicit":[63],"for":[66,153],"training.Building":[67],"on":[68,84],"this,":[69],"propose":[71],"HyPeR,":[72],"two-stage":[74],"Hybrid":[75],"Perception-Reasoning":[76],"framework.In":[77],"Stage":[78,93],"I,":[79],"finetune":[81],"model":[83],"PAQA":[85],"to":[86,98,108,121,143],"perceive":[87],"acoustic":[88],"attributes":[89],"complex":[91],"audio.In":[92],"II,":[94],"leverage":[96],"GRPO":[97],"refine":[99],"internal":[102],"deliberation.We":[103],"also":[104],"PAUSE":[106],"tokens":[107],"facilitate":[109],"latent":[110],"computation":[111],"during":[112],"acoustically":[113],"ambiguous":[114],"phases":[115],"design":[117],"consistency":[119],"reward":[120],"align":[122],"rationales":[124],"with":[125,140],"raw":[126],"audio.Experiments":[127],"across":[128],"benchmarks":[129],"demonstrate":[130],"HyPeR":[132],"achieves":[133],"absolute":[134],"improvements":[135],"over":[136],"base":[138],"model,":[139],"performance":[141],"comparable":[142],"large-scale":[144],"models,":[145],"stressing":[146],"effectiveness":[148],"of":[149],"hybrid":[150],"perception-grounded":[151],"robust":[154],"multi-speaker":[156],"understanding.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}