{"id":"https://openalex.org/W3209900408","doi":"https://doi.org/10.1145/3474085.3475529","title":"Actions Speak Louder than Listening","display_name":"Actions Speak Louder than Listening","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3209900408","doi":"https://doi.org/10.1145/3474085.3475529","mag":"3209900408"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070642261","display_name":"Wei-Tsung Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Tsung Lu","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc","Academia Sinica ,Taipei, Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica ,Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082426239","display_name":"Meng-Hsuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1321014770","display_name":"Association for Computing Machinery","ror":"https://ror.org/03wsadn68","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1321014770"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Meng-Hsuan Wu","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc","Association for Computing Machinery"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Association for Computing Machinery","institution_ids":["https://openalex.org/I1321014770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080043841","display_name":"Yuh-Ming Chiu","orcid":"https://orcid.org/0000-0002-2208-8010"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuh-Ming Chiu","raw_affiliation_strings":["KKBOX, Inc., Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KKBOX, Inc., Taipei, Taiwan Roc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101659148","display_name":"Li Su","orcid":"https://orcid.org/0009-0007-7183-8432"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc","Academia Sinica ,Taipei, Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica ,Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14298946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3936","last_page":"3944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9994999766349792,"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":0.9983999729156494,"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":0.7876051664352417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778528928756714},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5787506699562073},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5195584297180176},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5006639957427979},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.500098466873169},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48584267497062683},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.45520734786987305},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.4252949357032776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3462541401386261},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33510857820510864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3307432532310486},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32671183347702026},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11451372504234314},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10433131456375122},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08166036009788513},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.07042202353477478}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7876051664352417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778528928756714},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5787506699562073},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5195584297180176},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5006639957427979},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.500098466873169},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48584267497062683},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.45520734786987305},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.4252949357032776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3462541401386261},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33510857820510864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3307432532310486},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32671183347702026},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11451372504234314},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10433131456375122},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08166036009788513},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.07042202353477478},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"mag:3209900408","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2129192849","https://openalex.org/W2267126114","https://openalex.org/W2511667032","https://openalex.org/W2586947700","https://openalex.org/W2606176153","https://openalex.org/W2747023714","https://openalex.org/W2753868141","https://openalex.org/W2754229890","https://openalex.org/W2774077477","https://openalex.org/W2782490852","https://openalex.org/W2793183272","https://openalex.org/W2891757161","https://openalex.org/W2898827701","https://openalex.org/W2902922910","https://openalex.org/W2904596301","https://openalex.org/W2936497627","https://openalex.org/W2949382160","https://openalex.org/W2951535099","https://openalex.org/W2954914497","https://openalex.org/W2962699318","https://openalex.org/W2962775980","https://openalex.org/W2962968839","https://openalex.org/W2963032576","https://openalex.org/W2963341956","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2963575853","https://openalex.org/W2986842658","https://openalex.org/W2989656344","https://openalex.org/W2991377373","https://openalex.org/W3011240691","https://openalex.org/W3021164770","https://openalex.org/W3034758887","https://openalex.org/W3035435378","https://openalex.org/W3092879656","https://openalex.org/W3106383471","https://openalex.org/W3124507227","https://openalex.org/W3141966616"],"related_works":["https://openalex.org/W10664707","https://openalex.org/W5937335","https://openalex.org/W2367263","https://openalex.org/W4323835","https://openalex.org/W270053","https://openalex.org/W7679584","https://openalex.org/W14696333","https://openalex.org/W1697743","https://openalex.org/W8907840","https://openalex.org/W10171396"],"abstract_inverted_index":{"The":[0,169],"subjective":[1],"evaluation":[2],"of":[3,39,88,106,114,119,172,179],"music":[4,20,40,54,131,190],"generation":[5,41],"techniques":[6],"has":[7],"been":[8],"mostly":[9],"done":[10],"with":[11,92],"questionnaire-based":[12],"listening":[13,95,167],"tests":[14],"while":[15,187],"ignoring":[16],"the":[17,59,66,74,78,86,89,98,104,112,117,140,143,150,155,176,180,184,188],"perspectives":[18],"from":[19,73,165],"composition,":[21],"arrangement,":[22],"and":[23,65,97,122,183],"soundtrack":[24],"editing.":[25],"In":[26],"this":[27,173],"paper,":[28],"we":[29,50,84],"propose":[30],"an":[31,71],"editing":[32,37,100,151,156,181],"test":[33,96,152,157,182],"to":[34,128],"evaluate":[35],"users'":[36],"experience":[38],"models":[42,64,91],"in":[43,102],"a":[44,52,93,130],"systematic":[45,177],"way.":[46],"To":[47],"do":[48],"this,":[49],"design":[51],"new":[53],"style":[55,80,191],"transfer":[56,81,192],"model":[57,76,145,193],"combining":[58],"non-chronological":[60],"inference":[61],"architecture,":[62],"autoregressive":[63],"Transformer,":[67],"which":[68,103,161],"serves":[69],"as":[70],"improvement":[72,141],"baseline":[75,144],"on":[77,134,195],"same":[79],"task.":[82],"Then,":[83],"compare":[85],"performance":[87],"two":[90,135],"conventional":[94],"proposed":[99,189],"test,":[101],"quality":[105],"generated":[107],"samples":[108],"is":[109,175],"assessed":[110],"by":[111,126,149],"amount":[113],"effort":[115],"(e.g.,":[116],"number":[118],"required":[120],"keyboard":[121],"mouse":[123],"actions)":[124],"spent":[125],"users":[127],"polish":[129],"clip.":[132],"Results":[133],"target":[136],"styles":[137],"indicate":[138],"that":[139],"over":[142],"can":[146],"be":[147],"reflected":[148],"quantitatively.":[153],"Also,":[154],"provides":[158],"profound":[159],"insights":[160],"are":[162],"not":[163],"accessible":[164],"usual":[166],"tests.":[168],"major":[170],"contribution":[171],"paper":[174],"presentation":[178],"corresponding":[185],"insights,":[186],"based":[194],"state-of-the-art":[196],"neural":[197],"networks":[198],"represents":[199],"another":[200],"contribution.":[201]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}