{"id":"https://openalex.org/W7204180207","doi":"https://doi.org/10.18653/2026.findings-emnlp.2196","title":"MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models","display_name":"MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204180207","doi":"https://doi.org/10.18653/2026.findings-emnlp.2196"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.2196","doi":"https://doi.org/10.18653/2026.findings-emnlp.2196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2196","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2196.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-emnlp.2196.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148118802","display_name":"Yize Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yize Li","raw_affiliation_strings":["Bose Corporation","Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136221725","display_name":"Ningyuan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ningyuan Yang","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136266295","display_name":"Sile Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sile Yin","raw_affiliation_strings":["Bose Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136154773","display_name":"Sindhuja Thogarrati","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sindhuja Thogarrati","raw_affiliation_strings":["Bose Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079385080","display_name":"Sung-En Chang","orcid":"https://orcid.org/0000-0001-8585-503X","observed_orcids":["https://orcid.org/0000-0001-8585-503X"]},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sung-En Chang","raw_affiliation_strings":["Bose Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148125699","display_name":"Andrew C. Singer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew C. Singer","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372168","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0001-7934-5682","observed_orcids":["https://orcid.org/0000-0001-7934-5682"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue Lin","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026007053","display_name":"Chuan-Che Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuan-Che Huang","raw_affiliation_strings":["Bose Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148065309","display_name":"Shuo Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Bose Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation","institution_ids":["https://openalex.org/I76587968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2896,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9501933,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"47028","last_page":"47054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.482699990272522,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.482699990272522,"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/T11309","display_name":"Music and Audio Processing","score":0.3752000033855438,"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/T10860","display_name":"Speech and Audio Processing","score":0.11169999837875366,"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/large-audio-language-models","display_name":"large audio language models","score":0.9089999794960022},{"id":"https://openalex.org/keywords/audio-quality-assessment","display_name":"audio quality assessment","score":0.5649999976158142},{"id":"https://openalex.org/keywords/speech-degradation","display_name":"speech degradation","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503999829292297},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28870001435279846}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.2196","doi":"https://doi.org/10.18653/2026.findings-emnlp.2196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2196","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2196.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.22236","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22236","pdf_url":"https://arxiv.org/pdf/2608.22236","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22236","doi":"https://doi.org/10.48550/arxiv.2608.22236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22236","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.2196","doi":"https://doi.org/10.18653/2026.findings-emnlp.2196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2196","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2196.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204180207.pdf","grobid_xml":"https://content.openalex.org/works/W7204180207.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2600556233","https://openalex.org/W3167533889","https://openalex.org/W3198020407","https://openalex.org/W4281736089","https://openalex.org/W4390041933","https://openalex.org/W4392679398","https://openalex.org/W4400717319","https://openalex.org/W4404330874","https://openalex.org/W4409051416","https://openalex.org/W4414588426","https://openalex.org/W4415202956","https://openalex.org/W4415255153","https://openalex.org/W4415310554","https://openalex.org/W4416035790","https://openalex.org/W4417142388","https://openalex.org/W6966994820","https://openalex.org/W7106292994","https://openalex.org/W7117988839","https://openalex.org/W7124753722","https://openalex.org/W7127310721","https://openalex.org/W7128730948","https://openalex.org/W7134245636","https://openalex.org/W7134823312","https://openalex.org/W7134977886","https://openalex.org/W7154207876","https://openalex.org/W7160175825","https://openalex.org/W7161267559","https://openalex.org/W7161733373","https://openalex.org/W7162515554","https://openalex.org/W7162694769","https://openalex.org/W7171360697","https://openalex.org/W7172394830"],"related_works":["https://openalex.org/W7222913541","https://openalex.org/W7212156359","https://openalex.org/W7083699623","https://openalex.org/W7106673227","https://openalex.org/W7213753621","https://openalex.org/W7164066912","https://openalex.org/W7139943444","https://openalex.org/W4417080425","https://openalex.org/W7155452472","https://openalex.org/W7134977886"],"abstract_inverted_index":{"Large":[0],"audio-language":[1,101,176],"models":[2,85,141],"(LALMs)":[3],"have":[4],"shown":[5],"promising":[6],"progress":[7],"in":[8,50,67],"understanding":[9,66,177],"speech,":[10,70],"music,":[11,71],"and":[12,65,72,74,93,115,134,165,178],"general":[13],"sound":[14],"events,":[15],"yet":[16,172],"their":[17],"ability":[18],"to":[19,86,132,148,190],"reason":[20,152],"about":[21,153],"how":[22],"audio":[23,38,51,62,82],"signals":[24],"are":[25,188],"degraded":[26],"remains":[27],"underexplored.Existing":[28],"benchmarks":[29],"primarily":[30],"evaluate":[31],"semantic":[32],"understanding,":[33],"event":[34],"recognition,":[35],"or":[36,151],"high-level":[37],"reasoning,":[39],"leaving":[40],"a":[41,55,123,159,170,180],"basic":[42],"question":[43],"unanswered:":[44],"Do":[45],"LALMs":[46,106,129,164,186],"understand":[47],"the":[48],"differences":[49],"quality?We":[52],"introduce":[53],"MRMAD,":[54],"Multi-Round":[56],"Multi-Audio":[57],"Degradation":[58],"benchmark":[59],"for":[60,183],"evaluating":[61],"degradation":[63,110],"perception":[64,161],"LALMs.MRMAD":[68],"spans":[69],"sound,":[73],"frames":[75],"evaluation":[76,125],"as":[77],"multi-turn":[78,121],"dialogues":[79],"across":[80,97],"multiple":[81],"inputs,":[83],"requiring":[84],"identify":[87],"types":[88],"of":[89,126,175],"degradation,":[90],"compare":[91],"severity,":[92],"perceive":[94],"corruption":[95],"changes":[96],"turns.Unlike":[98],"current":[99,140],"single-turn":[100],"benchmarks,":[102],"MR-MAD":[103],"evaluates":[104],"whether":[105],"can":[107],"maintain":[108],"consistent":[109],"hypotheses":[111],"with":[112],"new":[113],"evidence":[114],"comprehend":[116],"low-level":[117],"acoustic":[118,192],"phenomena":[119],"over":[120],"dialogues.Through":[122],"systematic":[124],"18":[127],"representative":[128],"from":[130],"non-thinking":[131],"reasoning":[133],"Omni":[135],"models,":[136],"we":[137],"find":[138],"that":[139,187],"often":[142],"recognize":[143],"coarse":[144],"content":[145],"while":[146],"failing":[147],"diagnose,":[149],"compare,":[150],"degradations":[154],"reliably.Human":[155],"evaluations":[156],"further":[157],"reveal":[158],"significant":[160],"gap":[162],"between":[163],"human":[166],"listeners.MRMAD":[167],"thus":[168],"exposes":[169],"critical":[171],"overlooked":[173],"aspect":[174],"provides":[179],"diagnostic":[181],"foundation":[182],"building":[184],"future":[185],"robust":[189],"real-world":[191],"conditions":[193],"1":[194],".":[195]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-26T00:00:00"}