{"id":"https://openalex.org/W7108696751","doi":"https://doi.org/10.5281/zenodo.17811361","title":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks","display_name":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108696751","doi":"https://doi.org/10.5281/zenodo.17811361"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811361","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811361","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811361","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yongyi Zang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongyi Zang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sean O'Brien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sean O'Brien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Taylor  Berg-Kirkpatrick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taylor  Berg-Kirkpatrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Julian  McAuley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian  McAuley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zachary Novack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zachary Novack","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7261999845504761,"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":0.7261999845504761,"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/T10028","display_name":"Topic Modeling","score":0.03099999949336052,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.016499999910593033,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7483999729156494},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.41929998993873596},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.3472000062465668},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.32269999384880066}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7483999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.32269999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.2921000123023987},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2847000062465668}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811361","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811361","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811361","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811361","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6031550168991089,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Audio":[1],"Language":[2],"Models":[3],"(LALMs),":[4],"where":[5],"pretrained":[6],"text":[7],"LLMs":[8,37,158],"are":[9,170],"finetuned":[10],"with":[11,57,172],"audio":[12,39,82,115,141,168,187],"input,":[13],"have":[14],"made":[15],"remarkable":[16],"progress":[17],"in":[18,97,180],"music":[19],"understanding.":[20],"However,":[21],"current":[22],"evaluation":[23,96],"methodologies":[24],"exhibit":[25],"critical":[26],"limitations:":[27],"on":[28,114,155],"the":[29,102],"leading":[30],"Music":[31],"Question":[32],"Answering":[33],"benchmark,":[34],"MuchoMusic,":[35,146],"text-only":[36,123],"without":[38],"perception":[40,116,188],"capabilities":[41],"achieve":[42],"surprisingly":[43],"high":[44],"accuracy":[45],"of":[46,62],"up":[47],"to":[48,134,145,153],"56.4%,":[49],"much":[50],"higher":[51],"than":[52,81],"chance.":[53,70],"Furthermore,":[54],"when":[55,167],"presented":[56],"random":[58],"Gaussian":[59],"noise":[60],"instead":[61],"actual":[63],"audio,":[64],"LALMs":[65,164],"still":[66],"perform":[67,159],"significantly":[68],"above":[69],"These":[71,174],"findings":[72],"suggest":[73],"existing":[74],"benchmarks":[75,182],"predominantly":[76],"assess":[77],"reasoning":[78],"abilities":[79],"rather":[80],"perception.":[83,142],"To":[84],"overcome":[85],"this":[86,127],"challenge,":[87],"we":[88,129],"present":[89],"RUListening,":[90],"a":[91,106,111],"framework":[92],"that":[93,109,138,183],"enhances":[94],"perceptual":[95,156],"Music-QA":[98],"benchmarks.":[99],"We":[100],"introduce":[101],"Perceptual":[103],"Index":[104],"(PI),":[105],"quantitative":[107],"metric":[108],"measures":[110],"question's":[112],"reliance":[113],"by":[117],"analyzing":[118],"log":[119],"probability":[120],"distributions":[121],"from":[122],"language":[124],"models.":[125],"Using":[126],"metric,":[128],"generate":[130],"synthetic,":[131],"challenging":[132],"distractors":[133],"create":[135],"QA":[136],"pairs":[137],"necessitate":[139],"genuine":[140],"When":[143],"applied":[144],"our":[147,177],"filtered":[148],"dataset":[149],"successfully":[150],"forces":[151],"models":[152],"rely":[154],"information\u2014text-only":[157],"at":[160],"chance":[161],"levels,":[162],"while":[163],"similarly":[165],"deteriorate":[166],"inputs":[169],"replaced":[171],"noise.":[173],"results":[175],"validate":[176],"framework's":[178],"effectiveness":[179],"creating":[181],"more":[184],"accurately":[185],"evaluate":[186],"capabilities.":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-12-05T00:00:00"}