{"id":"https://openalex.org/W7154007552","doi":"https://doi.org/10.1145/3772318.3791929","title":"MoXaRt: Audio-Visual Object-Guided Sound Interaction for XR","display_name":"MoXaRt: Audio-Visual Object-Guided Sound Interaction for XR","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154007552","doi":"https://doi.org/10.1145/3772318.3791929"},"language":null,"primary_location":{"id":"doi:10.1145/3772318.3791929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791929","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772318.3791929","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133516160","display_name":"Tianyu Xu","orcid":"https://orcid.org/0009-0009-9135-6080"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianyu Xu","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0009-9135-6080","affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022709364","display_name":"S. H. Kim","orcid":"https://orcid.org/0009-0005-4355-7241"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sieun Kim","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0009-0005-4355-7241","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qianhui Zheng","orcid":"https://orcid.org/0009-0008-5664-3431"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qianhui Zheng","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0009-0008-5664-3431","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133461492","display_name":"Ruoyu Iris Xu","orcid":"https://orcid.org/0009-0005-8323-5503"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruoyu Xu","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0005-8323-5503","affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114633768","display_name":"Tejasvi Ravi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tejasvi Ravi","raw_affiliation_strings":["Google, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-3260-5519","affiliations":[{"raw_affiliation_string":"Google, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078947104","display_name":"Anuva Kulkarni","orcid":"https://orcid.org/0000-0001-8896-7504"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuva Kulkarni","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8896-7504","affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128909773","display_name":"Katrina Passarella-Ward","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrina Passarella-Ward","raw_affiliation_strings":["Google, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0009-0000-8670-1833","affiliations":[{"raw_affiliation_string":"Google, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128375429","display_name":"Junyi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyi Zhu","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0001-6166-6138","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067691489","display_name":"Adarsh Kowdle","orcid":"https://orcid.org/0000-0002-4428-889X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adarsh Kowdle","raw_affiliation_strings":["Google, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4428-889X","affiliations":[{"raw_affiliation_string":"Google, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5133516160"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76988189,"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":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5837000012397766,"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":0.5837000012397766,"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/T12032","display_name":"Multisensory perception and integration","score":0.07800000160932541,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.07280000299215317,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4779999852180481},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.39570000767707825},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3506999909877777},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.34860000014305115},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3370000123977661},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.32010000944137573},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.30979999899864197},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649399995803833},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4700999855995178},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39570000767707825},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C2986659363","wikidata":"https://www.wikidata.org/wiki/Q6646450","display_name":"Listening comprehension","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C100142294","wikidata":"https://www.wikidata.org/wiki/Q2070426","display_name":"Selective auditory attention","level":4,"score":0.263700008392334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C171179263","wikidata":"https://www.wikidata.org/wiki/Q4820026","display_name":"Auditory display","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772318.3791929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791929","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3772318.3791929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791929","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.76451575756073,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1991139021","https://openalex.org/W2099940712","https://openalex.org/W2119647652","https://openalex.org/W2123649031","https://openalex.org/W2128213565","https://openalex.org/W2130736456","https://openalex.org/W2250384498","https://openalex.org/W2532511219","https://openalex.org/W2962865004","https://openalex.org/W3039819685","https://openalex.org/W3166898278","https://openalex.org/W3182657421","https://openalex.org/W3207910091","https://openalex.org/W3215786006","https://openalex.org/W3217017227","https://openalex.org/W4220871331","https://openalex.org/W4283031696","https://openalex.org/W4285231146","https://openalex.org/W4289665794","https://openalex.org/W4307977675","https://openalex.org/W4312909419","https://openalex.org/W4366777994","https://openalex.org/W4372348953","https://openalex.org/W4386065742","https://openalex.org/W4387835382","https://openalex.org/W4390642493","https://openalex.org/W4392903251","https://openalex.org/W4392903379","https://openalex.org/W4396833001","https://openalex.org/W4400142589","https://openalex.org/W4402521381","https://openalex.org/W4402954056","https://openalex.org/W4403334468","https://openalex.org/W4406265656","https://openalex.org/W4406774860","https://openalex.org/W4409749523","https://openalex.org/W4413968373","https://openalex.org/W4416184226","https://openalex.org/W4417199954","https://openalex.org/W7084054188"],"related_works":[],"abstract_inverted_index":{"In":[0],"Extended":[1],"Reality":[2],"(XR),":[3],"complex":[4,75],"acoustic":[5,142],"environments":[6,143],"often":[7],"overwhelm":[8],"users,":[9],"compromising":[10],"both":[11],"scene":[12],"awareness":[13],"and":[14,37,113,115,159],"social":[15],"engagement":[16],"due":[17],"to":[18,33,70,79],"entangled":[19],"sound":[20,40],"sources.":[21],"We":[22,95],"introduce":[23],"MoXaRt,":[24],"a":[25,45,99,103,116,131],"real-time":[26],"XR":[27,162],"system":[28,125],"that":[29,48,123],"uses":[30],"audio-visual":[31],"cues":[32],"separate":[34],"these":[35],"sources":[36,59,82],"enable":[38],"fine-grained":[39],"interaction.":[41],"MoXaRt\u2019s":[42],"core":[43],"is":[44],"cascaded":[46],"architecture":[47],"performs":[49],"coarse,":[50],"audio-only":[51],"separation":[52],"in":[53,137],"parallel":[54],"with":[55,89],"visual":[56,64],"detection":[57],"of":[58,77,106],"(e.g.,":[60,83],"faces,":[61],"instruments).":[62],"These":[63],"anchors":[65],"then":[66],"guide":[67],"refinement":[68],"networks":[69],"isolate":[71],"individual":[72],"sources,":[73],"separating":[74],"mixes":[76],"up":[78],"5":[80],"concurrent":[81,111],"2":[84,91],"voices":[85],"+":[86],"3":[87],"instruments)":[88],"\u223c":[90],"second":[92],"processing":[93],"latency.":[94],"validate":[96],"MoXaRt":[97],"through":[98],"technical":[100],"evaluation":[101],"on":[102],"new":[104],"dataset":[105],"30":[107],"one-minute":[108],"recordings":[109],"featuring":[110],"speech":[112,128],"music,":[114],"22-participant":[117],"user":[118],"study.":[119],"Empirical":[120],"results":[121],"indicate":[122],"our":[124],"significantly":[126],"enhances":[127],"intelligibility,":[129],"yielding":[130],"36.2%":[132],"(p":[133,149],"<":[134,150],"0.01)":[135],"increase":[136],"listening":[138],"comprehension":[139],"within":[140],"adversarial":[141],"while":[144],"substantially":[145],"reducing":[146],"cognitive":[147],"load":[148],"0.001),":[151],"thereby":[152],"paving":[153],"the":[154],"way":[155],"for":[156],"more":[157],"perceptive":[158],"socially":[160],"adept":[161],"experiences.":[163]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-14T00:00:00"}