{"id":"https://openalex.org/W4408351833","doi":"https://doi.org/10.1109/icassp49660.2025.10889814","title":"Audiopedia: Audio QA with Knowledge","display_name":"Audiopedia: Audio QA with Knowledge","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351833","doi":"https://doi.org/10.1109/icassp49660.2025.10889814"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1924388/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009838940","display_name":"Abhirama Subramanyam Penamakuri","orcid":"https://orcid.org/0000-0003-3646-8492"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhirama Subramanyam Penamakuri","raw_affiliation_strings":["Indian Institute of Technology Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115728997","display_name":"Kiran Chhatre","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Kiran Chhatre","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115728998","display_name":"Akshat Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akshat Jain","raw_affiliation_strings":["Indian Institute of Technology Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.03773076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9934999942779541,"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":0.9934999942779541,"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":0.9736999869346619,"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":0.9448000192642212,"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/computer-science","display_name":"Computer science","score":0.7724734544754028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724734544754028}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-358060","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-358060","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1924388/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-358060","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-358060","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1924388/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408351833.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2277195237","https://openalex.org/W2557764419","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2945844671","https://openalex.org/W2962910007","https://openalex.org/W2963323070","https://openalex.org/W2963541336","https://openalex.org/W2963748441","https://openalex.org/W2964243274","https://openalex.org/W2966317026","https://openalex.org/W2987086322","https://openalex.org/W3044495139","https://openalex.org/W3099700870","https://openalex.org/W3109643012","https://openalex.org/W3121304688","https://openalex.org/W4312846625","https://openalex.org/W4313014461","https://openalex.org/W4382202558","https://openalex.org/W4385768011","https://openalex.org/W4385822863","https://openalex.org/W4389523839","https://openalex.org/W4391021627","https://openalex.org/W4404782634","https://openalex.org/W4404784428","https://openalex.org/W6756085085","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6861859833"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1,158],"paper,":[2],"we":[3,109],"introduce":[4],"Audiopedia,":[5],"a":[6,60,111],"novel":[7],"task":[8],"called":[9],"Audio":[10,26,50,79,133,140],"Question":[11,27,51,66,80],"Answering":[12,28,52,67,81],"with":[13,123],"Knowledge,":[14],"which":[15,69,83,147],"requires":[16,70],"both":[17],"audio":[18,38,62,74,87,95,167],"comprehension":[19],"and":[20,76,102,137],"external":[21],"knowledge":[22,124],"reasoning.":[23],"Unlike":[24],"traditional":[25],"(AQA)":[29],"benchmarks":[30],"that":[31,114],"focus":[32],"on":[33,59,99,151],"simple":[34],"queries":[35],"answerable":[36],"from":[37],"alone,":[39],"Audiopedia":[40],"targets":[41],"knowledge-intensive":[42,152,170],"questions.":[43],"We":[44,92,174],"define":[45],"three":[46],"sub-tasks:":[47],"(i)":[48,132],"Single":[49],"(s-AQA),":[53],"where":[54],"questions":[55],"are":[56],"answered":[57],"based":[58],"single":[61],"sample,":[63],"(ii)":[64,138],"Multi-Audio":[65],"(m-AQA),":[68],"reasoning":[71,125],"over":[72],"multiple":[73],"samples,":[75],"(iii)":[77],"Retrieval-Augmented":[78],"(r-AQA),":[82],"involves":[84],"retrieving":[85],"relevant":[86],"to":[88,118,163],"answer":[89],"the":[90,160],"question.":[91],"benchmark":[93],"large":[94],"language":[96],"models":[97],"(LALMs)":[98],"these":[100],"sub-tasks":[101],"observe":[103],"suboptimal":[104],"performance.":[105],"To":[106,155],"address":[107,164],"this,":[108],"propose":[110],"generic":[112],"framework":[113,128],"can":[115],"be":[116],"adapted":[117],"any":[119],"LALM,":[120],"equipping":[121],"them":[122],"capabilities.":[126],"Our":[127],"has":[129],"two":[130],"components:":[131],"Entity":[134],"Linking":[135],"(AEL)":[136],"Knowledge-Augmented":[139],"Large":[141],"Multimodal":[142],"Model":[143],"(KA<sup":[144],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>LM),":[146],"together":[148],"improve":[149],"performance":[150],"AQA":[153],"tasks.":[154],"our":[156,176],"knowledge,":[157],"is":[159],"first":[161],"work":[162],"advanced":[165],"speech":[166],"understanding":[168],"through":[169],"tasks":[171],"like":[172],"Audiopedia.":[173],"make":[175],"data":[177],"publicly":[178],"available:":[179],"https://abhiram4572.github.io/projects/audiopedia/.":[180]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}