{"id":"https://openalex.org/W7134965261","doi":"https://doi.org/10.5334/tismir.223","title":"Investigating Auditory\u2013Visual Perception Using Multi-Modal Neural Networks with the SoundActions Dataset","display_name":"Investigating Auditory\u2013Visual Perception Using Multi-Modal Neural Networks with the SoundActions Dataset","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7134965261","doi":"https://doi.org/10.5334/tismir.223"},"language":"en","primary_location":{"id":"doi:10.5334/tismir.223","is_oa":true,"landing_page_url":"https://doi.org/10.5334/tismir.223","pdf_url":"https://transactions.ismir.net/articles/223/files/69b13399e9a51.pdf","source":{"id":"https://openalex.org/S4210180030","display_name":"Transactions of the International Society for Music Information Retrieval","issn_l":"2514-3298","issn":["2514-3298"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the International Society for Music Information Retrieval","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://transactions.ismir.net/articles/223/files/69b13399e9a51.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128752074","display_name":"Jinyue Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I1823064","display_name":"Norwegian Academy of Music","ror":"https://ror.org/052dy9793","country_code":"NO","type":"education","lineage":["https://openalex.org/I1823064"]},{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Jinyue Guo","raw_affiliation_strings":["Department of Musicology , University of Oslo , Oslo , Norway","RITMO Centre for Interdisciplinary Studies in Rhythm , Time and Motion , University of Oslo , Oslo , Norway ;"],"affiliations":[{"raw_affiliation_string":"Department of Musicology , University of Oslo , Oslo , Norway","institution_ids":["https://openalex.org/I1823064","https://openalex.org/I184942183"]},{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm , Time and Motion , University of Oslo , Oslo , Norway ;","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071144214","display_name":"Jim T\u00f8rresen","orcid":"https://orcid.org/0000-0003-0556-0288"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jim T\u00f8rresen","raw_affiliation_strings":["RITMO Centre for Interdisciplinary Studies in Rhythm , Time and Motion , University of Oslo , Oslo , Norway ;"],"affiliations":[{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm , Time and Motion , University of Oslo , Oslo , Norway ;","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122359629","display_name":"Alexander Refsum Jensenius","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Alexander Refsum Jensenius","raw_affiliation_strings":["RITMO Centre for Interdisciplinary Studies in Rhythm , Time and Motion , University of Oslo , Oslo , Norway ;"],"affiliations":[{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm , Time and Motion , University of Oslo , Oslo , Norway ;","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5128752074"],"corresponding_institution_ids":["https://openalex.org/I1823064","https://openalex.org/I184942183"],"apc_list":{"value":300,"currency":"GBP","value_usd":367},"apc_paid":{"value":300,"currency":"GBP","value_usd":367},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92357724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"1","first_page":"66","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3458999991416931,"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":0.3458999991416931,"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":0.14390000700950623,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.07199999690055847,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.555400013923645},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44519999623298645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3407000005245209},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2718999981880188},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.266400009393692}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026999950408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5835000276565552},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5334/tismir.223","is_oa":true,"landing_page_url":"https://doi.org/10.5334/tismir.223","pdf_url":"https://transactions.ismir.net/articles/223/files/69b13399e9a51.pdf","source":{"id":"https://openalex.org/S4210180030","display_name":"Transactions of the International Society for Music Information Retrieval","issn_l":"2514-3298","issn":["2514-3298"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the International Society for Music Information Retrieval","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5334/tismir.223","is_oa":true,"landing_page_url":"https://doi.org/10.5334/tismir.223","pdf_url":"https://transactions.ismir.net/articles/223/files/69b13399e9a51.pdf","source":{"id":"https://openalex.org/S4210180030","display_name":"Transactions of the International Society for Music Information Retrieval","issn_l":"2514-3298","issn":["2514-3298"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the International Society for Music Information Retrieval","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.43718037009239197,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134965261.pdf","grobid_xml":"https://content.openalex.org/works/W7134965261.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W21347096","https://openalex.org/W2015394094","https://openalex.org/W2032337854","https://openalex.org/W2083235796","https://openalex.org/W2151096985","https://openalex.org/W2151394304","https://openalex.org/W2165371202","https://openalex.org/W2294798173","https://openalex.org/W2619383789","https://openalex.org/W3149839747","https://openalex.org/W3207758636","https://openalex.org/W4399422592","https://openalex.org/W4401960466"],"related_works":[],"abstract_inverted_index":{"Musicologists,":[0],"psychologists,":[1],"and":[2,9,16,20,35,38,62,127,143],"computer":[3],"scientists":[4],"study":[5],"relationships":[6],"between":[7,29],"auditory":[8],"visual":[10],"stimuli":[11],"from":[12],"very":[13],"different":[14],"perspectives":[15],"using":[17],"various":[18],"terminologies":[19],"methodologies.":[21],"This":[22],"article":[23],"aims":[24],"to":[25,65,135],"bridge":[26],"the":[27,43,74,77,86,97,106,112,116,121,130,136,146,161],"gap":[28],"phenomenological":[30],"sound":[31,55,78],"theory,":[32,34],"auditory\u2013visual":[33],"audio\u2013video":[36,50,98,108,162],"processing":[37],"machine":[39],"learning.":[40],"We":[41],"introduce":[42],"SoundActions":[44,117],"dataset,":[45,99,118],"a":[46],"collection":[47],"of":[48,52,69,76,85,148],"365":[49],"recordings":[51],"(primarily)":[53],"short":[54],"actions.":[56],"Each":[57],"recording":[58],"has":[59],"been":[60],"human\u2011labeled":[61],"annotated":[63],"according":[64],"Pierre":[66,155],"Schaeffer\u2019s":[67,156],"theory":[68,139],"reduced":[70],"listening,":[71],"which":[72],"describes":[73],"property":[75],"itself":[79],"(e.g.,":[80,88],"\u2018an":[81],"impulsive":[82],"sound\u2019)":[83],"instead":[84],"source":[87],"\u2018a":[89],"bird":[90],"sound\u2019).":[91],"With":[92],"these":[93],"reduced\u2011type":[94,113,125,166],"labels":[95,114],"in":[96,115],"we":[100],"conducted":[101],"two":[102],"experiments:":[103],"(1)":[104],"fine\u2011tuning":[105],"latest":[107],"transformer":[109],"model":[110,122,163],"on":[111,165],"proving":[119],"that":[120,129],"can":[123],"recognize":[124],"labels,":[126],"observing":[128],"modality\u2011imbalance":[131],"phenomenon":[132],"is":[133],"similar":[134],"added":[137],"value":[138],"by":[140,154],"Michel":[141],"Chion":[142],"(2)":[144],"proposing":[145],"Ensemble":[147],"Perception":[149],"Mode":[150],"Adapters":[151],"method":[152],"inspired":[153],"three":[157],"listening":[158],"modes,":[159],"improving":[160],"also":[164],"tasks.":[167]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2026-03-12T00:00:00"}
