{"id":"https://openalex.org/W3015635148","doi":"https://doi.org/10.1109/icassp40776.2020.9054108","title":"One-Shot Parametric Audio Production Style Transfer with Application to Frequency Equalization","display_name":"One-Shot Parametric Audio Production Style Transfer with Application to Frequency Equalization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015635148","doi":"https://doi.org/10.1109/icassp40776.2020.9054108","mag":"3015635148"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044396558","display_name":"Stylianos Ioannis Mimilakis","orcid":"https://orcid.org/0000-0003-4633-5538"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stylianos I. Mimilakis","raw_affiliation_strings":["Fraunhofer-IDMT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer-IDMT","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045694117","display_name":"Nicholas J. Bryan","orcid":"https://orcid.org/0000-0003-1469-7278"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas J. Bryan","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6573,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64646465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863184213638306},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7267298698425293},{"id":"https://openalex.org/keywords/equalization","display_name":"Equalization (audio)","score":0.6552468538284302},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.5778250694274902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5184875726699829},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5147731304168701},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5142133235931396},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4945347011089325},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4904929995536804},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4755289852619171},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4647582769393921},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4527398347854614},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.43321162462234497},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.34301823377609253},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2321610152721405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1779012382030487},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17259645462036133},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.14165446162223816},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11945179104804993},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11887872219085693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08699610829353333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863184213638306},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7267298698425293},{"id":"https://openalex.org/C75755367","wikidata":"https://www.wikidata.org/wiki/Q104531076","display_name":"Equalization (audio)","level":3,"score":0.6552468538284302},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.5778250694274902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5184875726699829},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5147731304168701},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5142133235931396},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4945347011089325},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4904929995536804},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4755289852619171},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4647582769393921},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4527398347854614},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.43321162462234497},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34301823377609253},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2321610152721405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1779012382030487},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17259645462036133},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.14165446162223816},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11945179104804993},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11887872219085693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08699610829353333},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-602765","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-602765.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/408949","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/408949","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W608300865","https://openalex.org/W1494445328","https://openalex.org/W1522301498","https://openalex.org/W1525353496","https://openalex.org/W1533861849","https://openalex.org/W1836465849","https://openalex.org/W1920280450","https://openalex.org/W2007466948","https://openalex.org/W2021123050","https://openalex.org/W2086381917","https://openalex.org/W2127589108","https://openalex.org/W2156172374","https://openalex.org/W2419603965","https://openalex.org/W2897524142","https://openalex.org/W2902653098","https://openalex.org/W2962926189","https://openalex.org/W2964105864","https://openalex.org/W2964121744","https://openalex.org/W2969372706","https://openalex.org/W2977593013","https://openalex.org/W3086644004","https://openalex.org/W3091905774","https://openalex.org/W4288346708","https://openalex.org/W6629525206","https://openalex.org/W6631190155","https://openalex.org/W6631587439","https://openalex.org/W6631943919","https://openalex.org/W6638667902","https://openalex.org/W6716956115","https://openalex.org/W6763039619","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2088690926","https://openalex.org/W1590604789","https://openalex.org/W1996547972","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W1611900921","https://openalex.org/W2155527258"],"abstract_inverted_index":{"Audio":[0],"production":[1,68],"is":[2,18],"a":[3,15,25,56,96,132],"difficult":[4],"process":[5,30],"for":[6],"many":[7],"people],":[8],"[and":[9],"properly":[10],"manipulating":[11],"sound":[12,44],"to":[13,39,46,109,114,122,131],"achieve":[14],"certain":[16],"effect":[17,35],"non-trivial.":[19],"In":[20],"this":[21,29],"paper],":[22],"[we":[23,90],"present":[24],"method":[26],"that":[27,76,105],"facilitates":[28],"by":[31],"inferring":[32],"appropriate":[33],"audio":[34,67,79,137],"parameters":[36,112],"in":[37,83],"order":[38],"make":[40],"an":[41,47],"input":[42],"recording":[43,121],"similar":[45],"unrelated":[48],"reference":[49],"recording.":[50],"We":[51],"frame":[52],"our":[53,88],"work":[54],"as":[55],"form":[57],"of":[58,94,119,135],"parametric":[59,136],"style":[60,80,118],"transfer":[61,81],"that],":[62],"[by":[63],"design],":[64],"[leverages":[65],"existing":[66],"semantics":[69],"and":[70,103],"manipulation":[71],"algorithms],":[72],"[avoiding":[73],"several":[74],"issues":[75],"have":[77],"plagued":[78],"algorithms":[82],"the":[84,92,111,116],"past.":[85],"To":[86],"demonstrate":[87],"approach],":[89],"consider":[91],"task":[93],"controlling":[95],"parametric],":[97],"[four-band":[98],"infinite":[99],"impulse":[100],"response":[101],"equalizer":[102],"show":[104],"we":[106,126],"are":[107],"able":[108],"predict":[110],"necessary":[113],"transform":[115],"equalization":[117],"one":[120],"another.":[123],"The":[124],"framework":[125],"present],":[127],"[however],":[128],"[is":[129],"applicable":[130],"wider":[133],"range":[134],"effects.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-04-17T00:00:00"}