{"id":"https://openalex.org/W4396833489","doi":"https://doi.org/10.1145/3613905.3650785","title":"Understanding the Use of AI-Based Audio Generation Models by End-Users","display_name":"Understanding the Use of AI-Based Audio Generation Models by End-Users","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396833489","doi":"https://doi.org/10.1145/3613905.3650785"},"language":"en","primary_location":{"id":"doi:10.1145/3613905.3650785","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613905.3650785","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3650785","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3650785","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043721574","display_name":"Jiyeon Han","orcid":"https://orcid.org/0009-0000-1580-8940"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiyeon Han","raw_affiliation_strings":["Computer Science and Engineering, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0009-0000-1580-8940","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035492918","display_name":"Eunseo Yang","orcid":"https://orcid.org/0009-0003-9654-2110"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunseo Yang","raw_affiliation_strings":["Computer Science and Engineering, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0009-0003-9654-2110","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058167732","display_name":"Uran Oh","orcid":"https://orcid.org/0000-0002-7832-6313"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Uran Oh","raw_affiliation_strings":["Computer Science and Engineering, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-7832-6313","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138925566"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9976000189781189,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9613999724388123,"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/computer-science","display_name":"Computer science","score":0.7701355814933777},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.726502537727356},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6936423778533936},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6053165793418884},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5617053508758545},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.5497673749923706},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41038447618484497},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3922906816005707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3805995583534241},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.30389583110809326},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1388566792011261},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09737980365753174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701355814933777},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.726502537727356},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6936423778533936},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6053165793418884},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5617053508758545},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.5497673749923706},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41038447618484497},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3922906816005707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3805995583534241},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.30389583110809326},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1388566792011261},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09737980365753174},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613905.3650785","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613905.3650785","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3650785","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613905.3650785","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613905.3650785","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613905.3650785","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1010102630","display_name":null,"funder_award_id":"RS-2022-00155966","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G1529969831","display_name":null,"funder_award_id":"RS-2022-00155966","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6919652826","display_name":null,"funder_award_id":"RS-2022-00155966","funder_id":"https://openalex.org/F4320321365","funder_display_name":"Ewha Womans University"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321365","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396833489.pdf","grobid_xml":"https://content.openalex.org/works/W4396833489.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W604972776","https://openalex.org/W1970224177","https://openalex.org/W2119570532","https://openalex.org/W2121277371","https://openalex.org/W2148730083","https://openalex.org/W2782255520","https://openalex.org/W2886697176","https://openalex.org/W2899724567","https://openalex.org/W2949950073","https://openalex.org/W2981731882","https://openalex.org/W3093215104","https://openalex.org/W3104194627","https://openalex.org/W3106118231","https://openalex.org/W3114618842","https://openalex.org/W3185341429","https://openalex.org/W3199400376","https://openalex.org/W4301393026","https://openalex.org/W4310230601","https://openalex.org/W4321275178","https://openalex.org/W4324070671","https://openalex.org/W4367359628","https://openalex.org/W4379466097","https://openalex.org/W4379548704","https://openalex.org/W4381786045","https://openalex.org/W4383617221","https://openalex.org/W4384520759","https://openalex.org/W6843330092"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W3135871143","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W2020966186","https://openalex.org/W296599067","https://openalex.org/W4387698063","https://openalex.org/W27741130","https://openalex.org/W2494533082"],"abstract_inverted_index":{"With":[0],"the":[1,7,92,104,110,114,127,140,143],"growing":[2],"popularity":[3],"of":[4,142],"video":[5],"platforms,":[6],"demand":[8],"for":[9,13,30,49,95,147],"copyright-free":[10],"audio":[11,50,63,144],"sources":[12],"adding":[14],"background":[15,81],"music":[16,82],"to":[17,22,54,61,78,138],"videos":[18],"is":[19,34],"also":[20],"expected":[21],"increase.":[23],"While":[24],"text-to-audio-generation":[25],"models":[26,48],"can":[27],"be":[28],"useful":[29],"this":[31],"purpose,":[32],"little":[33],"known":[35],"about":[36],"how":[37,46],"people":[38],"perceive":[39],"and":[40,53,58,99],"use":[41],"these":[42,132],"models.":[43],"To":[44],"understand":[45],"generation":[47,115,145],"are":[51],"used":[52],"identify":[55],"their":[56],"strengths":[57],"weaknesses":[59],"compared":[60],"typical":[62],"search":[64,93,97],"engines,":[65],"we":[66,134],"conducted":[67],"a":[68],"user":[69],"study":[70],"with":[71],"16":[72],"participants,":[73],"where":[74],"they":[75],"were":[76],"asked":[77],"choose":[79],"matching":[80],"after":[83],"watching":[84],"muted":[85],"videos.":[86],"Findings":[87],"show":[88],"that":[89],"participants":[90],"appreciate":[91],"engine":[94],"recommending":[96],"keywords":[98],"displaying":[100],"multiple":[101],"results":[102],"although":[103],"outcome":[105],"does":[106],"not":[107],"fully":[108],"reflect":[109],"intent.":[111],"In":[112],"contrast,":[113],"model":[116,146],"posed":[117],"challenges":[118],"in":[119,125],"choosing":[120],"proper":[121],"prompts":[122],"but":[123],"excelled":[124],"finding":[126],"desired":[128],"music.":[129],"Based":[130],"on":[131],"results,":[133],"suggest":[135],"design":[136],"considerations":[137],"improve":[139],"usability":[141],"end-users.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}