{"id":"https://openalex.org/W3207894480","doi":"https://doi.org/10.1109/icassp43922.2022.9746663","title":"Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks","display_name":"Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207894480","doi":"https://doi.org/10.1109/icassp43922.2022.9746663","mag":"3207894480"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746663","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5074113867","display_name":"Boyu Chen","orcid":"https://orcid.org/0000-0003-2397-7669"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Bo-Yu Chen","raw_affiliation_strings":["Academia Sinica,Research Center for IT Innovation,Taiwan","Research Center for IT Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for IT Innovation,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076379649","display_name":"Hsu Wei-Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Han Hsu","raw_affiliation_strings":["Academia Sinica,Research Center for IT Innovation,Taiwan","Research Center for IT Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for IT Innovation,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103537853","display_name":"Wei\u2010Hsiang Liao","orcid":"https://orcid.org/0000-0003-4113-1894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Hsiang Liao","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814826","display_name":"Marco A. Mart\u00ednez Ram\u00edrez","orcid":"https://orcid.org/0000-0002-3989-7519"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco A. Martinez Ramirez","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica,Research Center for IT Innovation,Taiwan","Research Center for IT Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for IT Innovation,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074113867"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":0.6119,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63161209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"470"},"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":0.9991000294685364,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9926000237464905,"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/differentiable-function","display_name":"Differentiable function","score":0.7633343935012817},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.723496675491333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6554012894630432},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6279681324958801},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5917172431945801},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5821338295936584},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4893783926963806},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.477705717086792},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43124592304229736},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.42803144454956055},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.42427176237106323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4075988829135895},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14142388105392456},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12267893552780151},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12050673365592957},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07805660367012024}],"concepts":[{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7633343935012817},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.723496675491333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6554012894630432},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6279681324958801},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5917172431945801},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5821338295936584},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4893783926963806},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.477705717086792},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43124592304229736},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.42803144454956055},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.42427176237106323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4075988829135895},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14142388105392456},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12267893552780151},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12050673365592957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07805660367012024},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746663","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1881549354","https://openalex.org/W1934212910","https://openalex.org/W2099471712","https://openalex.org/W2159306398","https://openalex.org/W2405656250","https://openalex.org/W2525312404","https://openalex.org/W2576859507","https://openalex.org/W2612445135","https://openalex.org/W2772600958","https://openalex.org/W2894398294","https://openalex.org/W2950060770","https://openalex.org/W2962271784","https://openalex.org/W2962939524","https://openalex.org/W2995233853","https://openalex.org/W3000389243","https://openalex.org/W3027521447","https://openalex.org/W3034268738","https://openalex.org/W3081154691","https://openalex.org/W3094893721","https://openalex.org/W3137000704","https://openalex.org/W3161037993","https://openalex.org/W3162289111","https://openalex.org/W3163547199","https://openalex.org/W3170365830","https://openalex.org/W3173589993","https://openalex.org/W3186853856","https://openalex.org/W4297775537","https://openalex.org/W4320013936","https://openalex.org/W6639490048","https://openalex.org/W6732421603","https://openalex.org/W6737664043","https://openalex.org/W6746401785","https://openalex.org/W6755630039","https://openalex.org/W6763945542","https://openalex.org/W6765949256","https://openalex.org/W6771763809","https://openalex.org/W6777879259","https://openalex.org/W6779394272","https://openalex.org/W6782310598","https://openalex.org/W6791783026","https://openalex.org/W6796739221"],"related_works":["https://openalex.org/W3005996785","https://openalex.org/W2953246223","https://openalex.org/W4328029048","https://openalex.org/W2914998939","https://openalex.org/W4293320219","https://openalex.org/W4288624664","https://openalex.org/W2809882560","https://openalex.org/W4289764804","https://openalex.org/W3180903229","https://openalex.org/W2903477224"],"abstract_inverted_index":{"A":[0],"central":[1],"task":[2],"of":[3,13,78,105,121],"a":[4,11,26,31,59,67,85,106,119],"Disc":[5],"Jockey":[6],"(DJ)":[7],"is":[8],"to":[9,35,61,74],"create":[10,36],"mixset":[12],"music":[14],"with":[15,118],"seamless":[16],"transitions":[17],"between":[18],"adjacent":[19],"tracks.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"explore":[25],"data-driven":[27],"approach":[28],"that":[29,87,110],"uses":[30,48],"generative":[32],"adversarial":[33],"network":[34],"the":[37,76,79,88,101,111],"song":[38],"transition":[39],"by":[40,66,95,100],"learning":[41],"from":[42],"real-world":[43],"DJ":[44],"mixes.":[45],"The":[46,71],"generator":[47,72],"two":[49,63],"differentiable":[50],"digital":[51],"signal":[52],"processing":[53],"components,":[54],"an":[55],"equalizer":[56],"(EQ)":[57],"and":[58,81],"fader,":[60],"mix":[62,90],"tracks":[64],"selected":[65],"data":[68],"generation":[69],"pipeline.":[70],"has":[73],"set":[75],"parameters":[77],"EQs":[80],"fader":[82],"in":[83],"such":[84],"way":[86],"resulting":[89],"resembles":[91],"real":[92],"mixes":[93],"created":[94],"human":[96],"DJ,":[97],"as":[98],"judged":[99],"discriminator":[102],"counterpart.":[103],"Result":[104],"listening":[107],"test":[108],"shows":[109],"model":[112],"can":[113],"achieve":[114],"competitive":[115],"results":[116],"compared":[117],"number":[120],"baselines.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}