{"id":"https://openalex.org/W4393970760","doi":"https://doi.org/10.1145/3640543.3645158","title":"SynthScribe: Deep Multimodal Tools for Synthesizer Sound Retrieval and Exploration","display_name":"SynthScribe: Deep Multimodal Tools for Synthesizer Sound Retrieval and Exploration","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4393970760","doi":"https://doi.org/10.1145/3640543.3645158"},"language":"en","primary_location":{"id":"doi:10.1145/3640543.3645158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645158","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645158","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","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/10.1145/3640543.3645158","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036136865","display_name":"Stephen Brade","orcid":"https://orcid.org/0009-0005-3182-1498"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Stephen Brade","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0005-3182-1498","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432451","display_name":"Bryan Wang","orcid":"https://orcid.org/0000-0001-9016-038X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bryan Wang","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9016-038X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050746489","display_name":"Maur\u00edcio Sousa","orcid":"https://orcid.org/0009-0007-8077-7205"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mauricio Sousa","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1438-2882","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093470844","display_name":"Gregory Lee Newsome","orcid":"https://orcid.org/0009-0003-6474-7509"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gregory Lee Newsome","raw_affiliation_strings":["Faculty of Music, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0003-6474-7509","affiliations":[{"raw_affiliation_string":"Faculty of Music, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082789942","display_name":"Sageev Oore","orcid":"https://orcid.org/0000-0002-8130-3569"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sageev Oore","raw_affiliation_strings":["Department of Computer Science, Dalhousie University, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8130-3569","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058485609","display_name":"Tovi Grossman","orcid":"https://orcid.org/0000-0002-0494-5373"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tovi Grossman","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0494-5373","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036136865"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.6576,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63224302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9915000200271606,"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":0.8197409510612488},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5377341508865356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5149722695350647},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5095603466033936},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4771506190299988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44509634375572205},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3379736542701721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197409510612488},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5377341508865356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5149722695350647},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5095603466033936},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4771506190299988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44509634375572205},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3379736542701721},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640543.3645158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645158","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645158","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3640543.3645158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645158","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645158","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393970760.pdf","grobid_xml":"https://content.openalex.org/works/W4393970760.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1998446618","https://openalex.org/W2024236092","https://openalex.org/W2051368408","https://openalex.org/W2099854727","https://openalex.org/W2115083233","https://openalex.org/W2146950091","https://openalex.org/W2169003314","https://openalex.org/W2347183436","https://openalex.org/W2755741438","https://openalex.org/W2795434834","https://openalex.org/W2796261470","https://openalex.org/W2940678350","https://openalex.org/W2955263139","https://openalex.org/W2982527219","https://openalex.org/W2993124604","https://openalex.org/W4206908526","https://openalex.org/W4285367203","https://openalex.org/W4307476004","https://openalex.org/W4312933868"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W2140798747","https://openalex.org/W611303608","https://openalex.org/W2948169060","https://openalex.org/W4313595395"],"abstract_inverted_index":{"Synthesizers":[0],"are":[1],"powerful":[2],"tools":[3],"that":[4,46,177],"allow":[5],"musicians":[6,20,180],"to":[7,21,28,51,87,144,172],"create":[8,173],"dynamic":[9],"and":[10,82,122,135,164],"original":[11],"sounds.":[12,34],"Existing":[13],"commercial":[14],"interfaces":[15],"for":[16,102,138],"synthesizers":[17],"typically":[18],"require":[19],"interact":[22],"with":[23,94,142],"complex":[24],"low-level":[25],"parameters":[26,141],"or":[27,147],"manage":[29],"large":[30,104],"libraries":[31],"of":[32,69,106,153,161],"premade":[33],"To":[35],"address":[36,66],"these":[37],"challenges,":[38],"we":[39],"implement":[40,63],"SynthScribe":[41,158],"\u2014":[42],"a":[43,58,67,88,98,103,109,128,145,179],"fullstack":[44],"system":[45],"uses":[47],"multimodal":[48,99],"deep":[49],"learning":[50],"let":[52],"users":[53,126],"express":[54],"their":[55],"intentions":[56],"at":[57],"much":[59],"higher":[60],"level.":[61],"We":[62],"features":[64],"which":[65,115,133],"number":[68],"difficulties,":[70],"namely":[71],"1)":[72],"searching":[73],"through":[74],"existing":[75],"sounds,":[76,81],"2)":[77],"creating":[78],"completely":[79,116,174],"new":[80,117,175],"3)":[83],"making":[84],"meaningful":[85],"modifications":[86],"given":[89,124],"sound.":[90],"This":[91],"is":[92,159],"achieved":[93],"three":[95],"main":[96],"features:":[97],"search":[100],"engine":[101],"library":[105],"synthesizer":[107],"sounds;":[108],"user":[110,155],"centered":[111],"genetic":[112],"algorithm":[113],"by":[114],"sounds":[118,166,176],"can":[119],"be":[120],"created":[121],"selected":[123],"the":[125,170],"preferences;":[127],"sound":[129],"editing":[130],"support":[131],"feature":[132],"highlights":[134],"gives":[136],"examples":[137],"key":[139],"control":[140],"respect":[143],"text":[146],"audio":[148],"based":[149],"query.":[150],"The":[151],"results":[152],"our":[154],"studies":[156],"show":[157],"capable":[160],"reliably":[162],"retrieving":[163],"modifying":[165],"while":[167],"also":[168],"affording":[169],"ability":[171],"expand":[178],"creative":[181],"horizon.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-04-06T00:00:00"}