{"id":"https://openalex.org/W4372341951","doi":"https://doi.org/10.1109/icassp49357.2023.10097250","title":"GANStrument: Adversarial Instrument Sound Synthesis with Pitch-Invariant Instance Conditioning","display_name":"GANStrument: Adversarial Instrument Sound Synthesis with Pitch-Invariant Instance Conditioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341951","doi":"https://doi.org/10.1109/icassp49357.2023.10097250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5059687412","display_name":"Gaku Narita","orcid":"https://orcid.org/0000-0002-7150-3137"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gaku Narita","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan","Sony Computer Science Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]},{"raw_affiliation_string":"Sony Computer Science Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751033","display_name":"Junichi Shimizu","orcid":"https://orcid.org/0000-0002-3119-5272"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Shimizu","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan","Sony Computer Science Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]},{"raw_affiliation_string":"Sony Computer Science Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087426444","display_name":"Taketo Akama","orcid":"https://orcid.org/0009-0007-6971-2777"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taketo Akama","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan","Sony Computer Science Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]},{"raw_affiliation_string":"Sony Computer Science Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059687412"],"corresponding_institution_ids":["https://openalex.org/I4210122684"],"apc_list":null,"apc_paid":null,"fwci":1.1069,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79328765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9990000128746033,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8503169417381287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6889378428459167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5197926759719849},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5126880407333374},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4854010045528412},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46876972913742065},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4635993540287018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42970627546310425},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.41234689950942993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19159752130508423}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8503169417381287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6889378428459167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5197926759719849},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5126880407333374},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4854010045528412},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46876972913742065},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4635993540287018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42970627546310425},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.41234689950942993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19159752130508423},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W1878791236","https://openalex.org/W2000359198","https://openalex.org/W2120847449","https://openalex.org/W2519091744","https://openalex.org/W2606176153","https://openalex.org/W2621350877","https://openalex.org/W2787579267","https://openalex.org/W2803963372","https://openalex.org/W2910577860","https://openalex.org/W2948211236","https://openalex.org/W2963233633","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2989955315","https://openalex.org/W3000389243","https://openalex.org/W3035574324","https://openalex.org/W3092028330","https://openalex.org/W3136272958","https://openalex.org/W3208743843","https://openalex.org/W3215457199","https://openalex.org/W4224918993","https://openalex.org/W4281736089","https://openalex.org/W4285124635","https://openalex.org/W4286980377","https://openalex.org/W4290865547","https://openalex.org/W6637618735","https://openalex.org/W6736723571","https://openalex.org/W6739139180","https://openalex.org/W6748655329","https://openalex.org/W6758675244","https://openalex.org/W6763100362","https://openalex.org/W6765147365","https://openalex.org/W6767111847","https://openalex.org/W6771763809","https://openalex.org/W6782757012","https://openalex.org/W6783867762","https://openalex.org/W6801986474","https://openalex.org/W6802609832","https://openalex.org/W6838843145","https://openalex.org/W6846529734"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2165912799","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W3109975354","https://openalex.org/W2124576126"],"abstract_inverted_index":{"We":[0],"propose":[1],"GANStrument,":[2],"a":[3,12,64],"generative":[4],"adversarial":[5,60],"model":[6],"for":[7,63],"instrument":[8,23],"sound":[9,14],"synthesis.":[10],"Given":[11],"one-shot":[13],"as":[15],"input,":[16],"it":[17],"is":[18],"able":[19],"to":[20,52],"generate":[21],"pitched":[22],"sounds":[24,48],"that":[25,68,80,85],"reflect":[26],"the":[27,30,71],"timbre":[28,75],"of":[29,46,93],"input":[31,97],"within":[32],"an":[33,59],"interactive":[34],"time.":[35],"By":[36],"exploiting":[37],"instance":[38,89],"conditioning,":[39],"GANStrument":[40,81],"achieves":[41],"better":[42],"fidelity":[43],"and":[44,49,74,96],"diversity":[45],"synthesized":[47],"generalization":[50],"ability":[51],"various":[53],"inputs.":[54],"In":[55],"addition,":[56],"we":[57],"introduce":[58],"training":[61],"scheme":[62],"pitch-invariant":[65],"feature":[66],"extractor":[67],"significantly":[69],"improves":[70],"pitch":[72],"accuracy":[73],"consistency.":[76],"Experimental":[77],"results":[78],"show":[79],"outperforms":[82],"strong":[83],"baselines":[84],"do":[86],"not":[87],"use":[88],"conditioning":[90],"in":[91],"terms":[92],"generation":[94],"quality":[95],"editability.":[98],"Qualitative":[99],"examples":[100],"are":[101],"available":[102],"online":[103],"<sup":[104],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[106],".":[107]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}