{"id":"https://openalex.org/W7148532570","doi":"https://doi.org/10.1109/asru65441.2025.11434723","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","display_name":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148532570","doi":"https://doi.org/10.1109/asru65441.2025.11434723"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434723","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/A5087962449","display_name":"C. C. Yang","orcid":"https://orcid.org/0000-0002-3476-3802"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Kai Yang","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132815382","display_name":"Neo Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Neo Ho","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067489639","display_name":"Y. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Jyun Lee","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087962449"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85887592,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5509999990463257,"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":0.5509999990463257,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.16609999537467957,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.061799999326467514,"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/perception","display_name":"Perception","score":0.6344000101089478},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.47540000081062317},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.44290000200271606},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3573000133037567},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.35690000653266907},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.33320000767707825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024999856948853},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6344000101089478},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4259999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.420199990272522},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C100142294","wikidata":"https://www.wikidata.org/wiki/Q2070426","display_name":"Selective auditory attention","level":4,"score":0.29350000619888306},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434723","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5628190040588379}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2973049979","https://openalex.org/W3099143320","https://openalex.org/W3152884768","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3202070718","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W4226380987","https://openalex.org/W4285250921","https://openalex.org/W4312391725","https://openalex.org/W4375869259","https://openalex.org/W4385572928","https://openalex.org/W4385822439","https://openalex.org/W4389520380","https://openalex.org/W4391021627","https://openalex.org/W4392903468","https://openalex.org/W4394773771","https://openalex.org/W4401042420","https://openalex.org/W4401609216","https://openalex.org/W4402112098","https://openalex.org/W4402112110","https://openalex.org/W4402112198","https://openalex.org/W4402671717","https://openalex.org/W4402671820","https://openalex.org/W4402671982","https://openalex.org/W4404781855","https://openalex.org/W4404782601","https://openalex.org/W4404782655","https://openalex.org/W4404782967","https://openalex.org/W4404783281","https://openalex.org/W4404784428","https://openalex.org/W4406461433","https://openalex.org/W4406461631","https://openalex.org/W4406461677","https://openalex.org/W4406461695","https://openalex.org/W4408352589","https://openalex.org/W4408354168","https://openalex.org/W4411119642","https://openalex.org/W4415433526","https://openalex.org/W4415797422","https://openalex.org/W4416036439","https://openalex.org/W4416036756","https://openalex.org/W7131777177","https://openalex.org/W7133236469","https://openalex.org/W7133238265"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"the":[1,21,119],"internal":[2],"mechanisms":[3],"of":[4,25,89],"large":[5],"audio-language":[6],"models":[7],"(LALMs)":[8],"is":[9],"crucial":[10],"for":[11,85,121],"interpreting":[12],"their":[13],"behavior":[14],"and":[15,30,50,66],"improving":[16],"performance.":[17],"This":[18],"work":[19],"presents":[20],"first":[22],"in-depth":[23],"analysis":[24],"how":[26,44],"LALMs":[27,78],"internally":[28],"perceive":[29],"recognize":[31],"auditory":[32,83,115],"attributes.":[33],"By":[34],"applying":[35],"vocabulary":[36],"projection":[37],"on":[38,81,100],"three":[39],"state-of-the-art":[40],"LALMs,":[41],"we":[42,103],"track":[43],"attribute":[45,56,116],"information":[46,57,92],"evolves":[47],"across":[48],"layers":[49,72],"token":[51],"positions.":[52,98],"We":[53],"find":[54],"that":[55,67],"generally":[58],"decreases":[59],"with":[60,74],"layer":[61],"depth":[62],"when":[63],"recognition":[64],"fails,":[65],"resolving":[68],"attributes":[69,87],"at":[70,96],"earlier":[71],"correlates":[73],"better":[75],"accuracy.":[76],"Moreover,":[77],"heavily":[79],"rely":[80],"querying":[82],"inputs":[84],"predicting":[86],"instead":[88],"aggregating":[90],"necessary":[91],"in":[93],"hidden":[94],"states":[95],"attribute-mentioning":[97],"Based":[99],"our":[101],"findings,":[102],"demonstrate":[104],"a":[105],"method":[106],"to":[107],"enhance":[108],"LALMs.":[109],"Our":[110],"results":[111],"offer":[112],"insights":[113],"into":[114],"processing,":[117],"paving":[118],"way":[120],"future":[122],"improvements.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}