{"id":"https://openalex.org/W7148364979","doi":"https://doi.org/10.1109/asru65441.2025.11434671","title":"MEAN-RIR: Multi-Modal Environment-Aware Network for Robust Room Impulse Response Estimation","display_name":"MEAN-RIR: Multi-Modal Environment-Aware Network for Robust Room Impulse Response Estimation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148364979","doi":"https://doi.org/10.1109/asru65441.2025.11434671"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434671","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/A5132795914","display_name":"Jiajian Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajian Chen","raw_affiliation_strings":["University of Science and Technology of China,,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005098294","display_name":"Jiakang Chen","orcid":"https://orcid.org/0000-0003-1590-7492"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakang Chen","raw_affiliation_strings":["University of Science and Technology of China,,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353513","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-0652-3297"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817644","display_name":"Qing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China,,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132815837","display_name":"Yu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gao","raw_affiliation_strings":["Midea Group (Shanghai) Co.,Ltd.,,AI Research Center,,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co.,Ltd.,,AI Research Center,,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132793374","display_name":"Jun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132795914"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8585688,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9613000154495239,"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/T10860","display_name":"Speech and Audio Processing","score":0.9613000154495239,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.017100000753998756,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.004999999888241291,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.7129999995231628},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.49399998784065247},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47780001163482666},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.46619999408721924},{"id":"https://openalex.org/keywords/finite-impulse-response","display_name":"Finite impulse response","score":0.3953000009059906},{"id":"https://openalex.org/keywords/impulse-noise","display_name":"Impulse noise","score":0.387800008058548},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.7129999995231628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445000171661377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47780001163482666},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C127372701","wikidata":"https://www.wikidata.org/wiki/Q16979398","display_name":"Impulse noise","level":3,"score":0.387800008058548},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.38089999556541443},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34709998965263367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C85761212","wikidata":"https://www.wikidata.org/wiki/Q1974593","display_name":"Transient response","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434671","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2002507711","https://openalex.org/W2003894508","https://openalex.org/W2094721231","https://openalex.org/W2125336414","https://openalex.org/W2315749149","https://openalex.org/W2410879554","https://openalex.org/W2519758402","https://openalex.org/W2616802817","https://openalex.org/W2901243971","https://openalex.org/W2973231102","https://openalex.org/W3015338123","https://openalex.org/W3108332675","https://openalex.org/W3139813613","https://openalex.org/W3178031393","https://openalex.org/W3198454118","https://openalex.org/W4221167707","https://openalex.org/W4372341113","https://openalex.org/W4385822504","https://openalex.org/W4390872369","https://openalex.org/W4402716236","https://openalex.org/W4402727828","https://openalex.org/W4402754152","https://openalex.org/W4408352314","https://openalex.org/W7133216317","https://openalex.org/W7133243644"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"Multi-Modal":[4],"EnvironmentAware":[5],"Network":[6],"(MEAN-RIR),":[7],"which":[8,42],"uses":[9],"an":[10],"encoder-decoder":[11],"framework":[12],"to":[13,70,104,114],"predict":[14],"room":[15,34],"impulse":[16],"response":[17],"(RIR)":[18],"based":[19],"on":[20],"multi-level":[21],"environmental":[22],"information":[23],"from":[24],"audio,":[25],"visual,":[26],"and":[27,48,62,91],"textual":[28],"sources.":[29],"Specifically,":[30],"reverberant":[31],"speech":[32],"capturing":[33],"acoustic":[35,132],"properties":[36],"serves":[37],"as":[38,51],"the":[39,63,84,88,95,106,116],"primary":[40],"input,":[41],"is":[43,56],"combined":[44],"with":[45,128],"panoramic":[46],"images":[47],"text":[49],"descriptions":[50],"supplementary":[52],"inputs.":[53],"Each":[54],"input":[55],"processed":[57],"by":[58],"its":[59],"respective":[60],"encoder,":[61],"outputs":[64],"are":[65,112],"fed":[66],"into":[67],"cross-attention":[68],"modules":[69],"enable":[71],"effective":[72],"interaction":[73],"between":[74],"different":[75],"modalities.":[76],"The":[77,119],"MEAN-RIR":[78],"decoder":[79],"generates":[80],"two":[81,110],"distinct":[82],"components:":[83],"first":[85],"component":[86],"captures":[87],"direct":[89],"sound":[90],"early":[92],"reflections,":[93],"while":[94],"second":[96],"produces":[97],"masks":[98],"that":[99,122],"modulate":[100],"learnable":[101],"filtered":[102],"noise":[103],"synthesize":[105],"late":[107],"reverberation.":[108],"These":[109],"components":[111],"mixed":[113],"reconstruct":[115],"final":[117],"RIR.":[118],"results":[120],"show":[121],"MEANRIR":[123],"significantly":[124],"improves":[125],"RIR":[126],"estimation,":[127],"notable":[129],"gains":[130],"in":[131],"parameters.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}