{"id":"https://openalex.org/W4387801088","doi":"https://doi.org/10.1145/3586183.3606823","title":"Soundify: Matching Sound Effects to Video","display_name":"Soundify: Matching Sound Effects to Video","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4387801088","doi":"https://doi.org/10.1145/3586183.3606823"},"language":"en","primary_location":{"id":"doi:10.1145/3586183.3606823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3586183.3606823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606823","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 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606823","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000156461","display_name":"David Chuan-En Lin","orcid":"https://orcid.org/0000-0003-0116-0463"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Chuan-En Lin","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University, United States"],"raw_orcid":"https://orcid.org/0000-0003-0116-0463","affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008539913","display_name":"Anastasis Germanidis","orcid":"https://orcid.org/0009-0004-0005-8197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anastasis Germanidis","raw_affiliation_strings":["Runway, United States"],"raw_orcid":"https://orcid.org/0009-0004-0005-8197","affiliations":[{"raw_affiliation_string":"Runway, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026697305","display_name":"Crist\u00f3bal Valenzuela","orcid":"https://orcid.org/0000-0003-3809-4324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Crist\u00f3bal Valenzuela","raw_affiliation_strings":["Runway, United States"],"raw_orcid":"https://orcid.org/0000-0003-3809-4324","affiliations":[{"raw_affiliation_string":"Runway, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028709325","display_name":"Yining Shi","orcid":"https://orcid.org/0009-0002-6612-4703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yining Shi","raw_affiliation_strings":["Runway, United States"],"raw_orcid":"https://orcid.org/0009-0002-6612-4703","affiliations":[{"raw_affiliation_string":"Runway, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075763217","display_name":"Nikolas Martelaro","orcid":"https://orcid.org/0000-0002-1824-0243"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolas Martelaro","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University, United States"],"raw_orcid":"https://orcid.org/0000-0002-1824-0243","affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000156461"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.1108,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88412256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11439","display_name":"Video Analysis and Summarization","score":0.9972000122070312,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081300854682922},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.7825795412063599},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6427292823791504},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6038221120834351},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4607807695865631},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4285801947116852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4148092567920685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32030391693115234},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.31632739305496216},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.11838850378990173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081300854682922},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.7825795412063599},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6427292823791504},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6038221120834351},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4607807695865631},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4285801947116852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4148092567920685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32030391693115234},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.31632739305496216},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.11838850378990173},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"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:10.1145/3586183.3606823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3586183.3606823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606823","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 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3586183.3606823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3586183.3606823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606823","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 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387801088.pdf","grobid_xml":"https://content.openalex.org/works/W4387801088.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2058733260","https://openalex.org/W2118783153","https://openalex.org/W2119581172","https://openalex.org/W2121277371","https://openalex.org/W2537196324","https://openalex.org/W2619697695","https://openalex.org/W2962865004","https://openalex.org/W2963218389","https://openalex.org/W2963680395","https://openalex.org/W2963807156","https://openalex.org/W2964109005","https://openalex.org/W2964345931","https://openalex.org/W2988200020","https://openalex.org/W3007605881","https://openalex.org/W3037391061","https://openalex.org/W3046890131","https://openalex.org/W3093699630","https://openalex.org/W3093732029","https://openalex.org/W3105017218","https://openalex.org/W3108240585","https://openalex.org/W3135367836","https://openalex.org/W4307475423","https://openalex.org/W4360991782","https://openalex.org/W6780316881"],"related_works":["https://openalex.org/W2591723141","https://openalex.org/W2053430337","https://openalex.org/W2785782068","https://openalex.org/W2032030284","https://openalex.org/W4300189336","https://openalex.org/W3046792021","https://openalex.org/W3169342585","https://openalex.org/W2159773886","https://openalex.org/W2744841575","https://openalex.org/W4245925285"],"abstract_inverted_index":{"In":[0,77,102],"the":[1,15,30,62,65,110],"art":[2],"of":[3,32,89,99,112],"video":[4,36,93,116,121],"editing,":[5],"sound":[6],"helps":[7],"add":[8],"character":[9],"to":[10,35,52,64,73,92,120],"an":[11],"object":[12],"and":[13,67,71,129],"immerse":[14],"viewer":[16],"within":[17],"a":[18,44,55,78,96,103],"space.":[19],"Through":[20],"formative":[21],"interviews":[22],"with":[23,122],"professional":[24],"editors":[25,48,117],"(N=10),":[26],"we":[27,83,108],"found":[28],"that":[29,46,85],"task":[31,126],"adding":[33],"sounds":[34,51,63,91,119],"can":[37],"be":[38],"challenging.":[39],"This":[40],"paper":[41],"presents":[42],"Soundify,":[43],"system":[45],"assists":[47],"in":[49,114],"matching":[50,59,90],"video.":[53],"Given":[54],"video,":[56,66],"Soundify":[57,86,113],"identifies":[58],"sounds,":[60],"synchronizes":[61],"dynamically":[68],"adjusts":[69],"panning":[70],"volume":[72],"create":[74],"spatial":[75],"audio.":[76],"human":[79],"evaluation":[80],"study":[81,106],"(N=889),":[82],"show":[84],"is":[87],"capable":[88],"out-of-the-box":[94],"for":[95],"diverse":[97],"range":[98],"audio":[100],"categories.":[101],"within-subjects":[104],"expert":[105],"(N=12),":[107],"demonstrate":[109],"usefulness":[111],"helping":[115],"match":[118],"lighter":[123],"workload,":[124],"reduced":[125],"completion":[127],"time,":[128],"improved":[130],"usability.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
