{"id":"https://openalex.org/W2977735357","doi":"https://doi.org/10.1109/taslp.2019.2944568","title":"InverSynth: Deep Estimation of Synthesizer Parameter Configurations From Audio Signals","display_name":"InverSynth: Deep Estimation of Synthesizer Parameter Configurations From Audio Signals","publication_year":2019,"publication_date":"2019-10-02","ids":{"openalex":"https://openalex.org/W2977735357","doi":"https://doi.org/10.1109/taslp.2019.2944568","mag":"2977735357"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2944568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944568","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5077269072","display_name":"Oren Barkan","orcid":"https://orcid.org/0000-0002-5059-0905"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oren Barkan","raw_affiliation_strings":["Microsoft Corporation, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-5059-0905","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077819198","display_name":"David Tsiris","orcid":"https://orcid.org/0000-0003-1098-8246"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"id":"https://openalex.org/I4210141777","display_name":"Academic College of Tel Aviv-Yafo","ror":"https://ror.org/04cg6c004","country_code":"IL","type":"education","lineage":["https://openalex.org/I4210141777"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"David Tsiris","raw_affiliation_strings":["Tel Aviv University, Tel Aviv-Yafo, Israel"],"raw_orcid":"https://orcid.org/0000-0003-1098-8246","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv-Yafo, Israel","institution_ids":["https://openalex.org/I16391192","https://openalex.org/I4210141777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106732003","display_name":"Ori Katz","orcid":"https://orcid.org/0000-0002-7390-2406"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ori Katz","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083002103","display_name":"Noam Koenigstein","orcid":"https://orcid.org/0000-0001-8219-4512"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"id":"https://openalex.org/I4210141777","display_name":"Academic College of Tel Aviv-Yafo","ror":"https://ror.org/04cg6c004","country_code":"IL","type":"education","lineage":["https://openalex.org/I4210141777"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Noam Koenigstein","raw_affiliation_strings":["Tel Aviv University, Tel Aviv-Yafo, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv-Yafo, Israel","institution_ids":["https://openalex.org/I16391192","https://openalex.org/I4210141777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4644,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.65481858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"27","issue":"12","first_page":"2385","last_page":"2396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8069849014282227},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7729222774505615},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.5698608160018921},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5272309184074402},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4617147445678711},{"id":"https://openalex.org/keywords/subtractive-color","display_name":"Subtractive color","score":0.44359925389289856},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4236098527908325},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09504169225692749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0800970196723938},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07426717877388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069849014282227},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7729222774505615},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.5698608160018921},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5272309184074402},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4617147445678711},{"id":"https://openalex.org/C150799807","wikidata":"https://www.wikidata.org/wiki/Q374081","display_name":"Subtractive color","level":2,"score":0.44359925389289856},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4236098527908325},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09504169225692749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0800970196723938},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07426717877388},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2944568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944568","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1584772874","https://openalex.org/W1610356397","https://openalex.org/W1832693441","https://openalex.org/W1920280450","https://openalex.org/W1972798320","https://openalex.org/W2045135321","https://openalex.org/W2059652044","https://openalex.org/W2113895797","https://openalex.org/W2127302078","https://openalex.org/W2143612262","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2294070989","https://openalex.org/W2296610835","https://openalex.org/W2309627465","https://openalex.org/W2414894569","https://openalex.org/W2519091744","https://openalex.org/W2605641710","https://openalex.org/W2791716806","https://openalex.org/W2807487589","https://openalex.org/W2897524142","https://openalex.org/W2905015588","https://openalex.org/W2910800662","https://openalex.org/W2946947453","https://openalex.org/W2949382160","https://openalex.org/W2952230511","https://openalex.org/W2962926189","https://openalex.org/W2963369619","https://openalex.org/W2963446712","https://openalex.org/W2963466723","https://openalex.org/W2964106018","https://openalex.org/W2964121744","https://openalex.org/W2972162845","https://openalex.org/W2977593013","https://openalex.org/W2998704965","https://openalex.org/W4212863985","https://openalex.org/W4232703006","https://openalex.org/W4285719527","https://openalex.org/W4288346708","https://openalex.org/W4294170691","https://openalex.org/W6631190155","https://openalex.org/W6636600944","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6683738474","https://openalex.org/W6684191040","https://openalex.org/W6696768903","https://openalex.org/W6697451111","https://openalex.org/W6698213403","https://openalex.org/W6715395060","https://openalex.org/W6736333047","https://openalex.org/W6758322195","https://openalex.org/W6763039619"],"related_works":["https://openalex.org/W63093223","https://openalex.org/W2064042445","https://openalex.org/W1992507414","https://openalex.org/W1502270335","https://openalex.org/W3156046797","https://openalex.org/W2530685530","https://openalex.org/W2046641174","https://openalex.org/W2120307627","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Sound":[0],"synthesis":[1],"is":[2,51,59,80,119],"a":[3,17,46,83,94],"complex":[4],"field":[5],"that":[6,104,115,123],"requires":[7],"domain":[8],"expertise.":[9],"Manual":[10],"tuning":[11,43],"of":[12,61],"synthesizer":[13,41,64,85],"parameters":[14,42,65],"to":[15,44,125],"match":[16,45],"specific":[18],"sound":[19,28],"can":[20],"be":[21],"an":[22,37,120],"exhaustive":[23],"task,":[24],"even":[25,72],"for":[26,40],"experienced":[27],"engineers.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,113],"introduce":[34],"InverSynth":[35,50,79,108],"-":[36],"automatic":[38],"method":[39],"given":[47],"input":[48,69],"sound.":[49],"based":[52],"on":[53,82],"strided":[54],"convolutional":[55],"neural":[56],"networks":[57],"and":[58,71,93,101],"capable":[60],"inferring":[62],"the":[63,68,74,106,116,126],"configuration":[66],"from":[67,73],"spectrogram":[70],"raw":[75],"audio.":[76],"The":[77],"effectiveness":[78],"demonstrated":[81],"subtractive":[84],"with":[86],"four":[87],"frequency":[88],"modulated":[89],"oscillators,":[90],"envelope":[91],"generator":[92],"gater":[95],"effect.":[96],"We":[97],"present":[98],"extensive":[99],"quantitative":[100],"qualitative":[102],"results":[103],"showcase":[105],"superiority":[107],"over":[109],"several":[110],"baselines.":[111],"Furthermore,":[112],"show":[114],"network":[117],"depth":[118],"important":[121],"factor":[122],"contributes":[124],"prediction":[127],"accuracy.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}