{"id":"https://openalex.org/W4224918993","doi":"https://doi.org/10.1109/icassp43922.2022.9746826","title":"Adversarial Audio Synthesis Using a Harmonic-Percussive Discriminator","display_name":"Adversarial Audio Synthesis Using a Harmonic-Percussive Discriminator","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918993","doi":"https://doi.org/10.1109/icassp43922.2022.9746826"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746826","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/A5100413513","display_name":"Ji\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-9864-5485"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jihyun Lee","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075112605","display_name":"Hyungseob Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungseob Lim","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101818678","display_name":"Chan\u2010Woo Lee","orcid":"https://orcid.org/0000-0002-0567-0527"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Lee","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059001612","display_name":"Inseon Jang","orcid":"https://orcid.org/0000-0003-2237-2668"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inseon Jang","raw_affiliation_strings":["Electronics and Telecommunications Research Institution,Daejeon,South Korea","Electronics and Telecommunications Research Institution, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institution,Daejeon,South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institution, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100413513"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47045814,"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":"961","last_page":"965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.996999979019165,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9950000047683716,"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/discriminator","display_name":"Discriminator","score":0.9580812454223633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6924092769622803},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6398725509643555},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5935963988304138},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5847448110580444},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5675413012504578},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.47269487380981445},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.41139906644821167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35006070137023926},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2922919988632202},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.27050602436065674},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13160374760627747},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.08910122513771057},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.08804497122764587}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9580812454223633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924092769622803},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6398725509643555},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5935963988304138},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5847448110580444},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5675413012504578},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.47269487380981445},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41139906644821167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35006070137023926},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2922919988632202},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27050602436065674},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13160374760627747},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.08910122513771057},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.08804497122764587},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746826","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":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1561135842","https://openalex.org/W2407513162","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2593414223","https://openalex.org/W2746068898","https://openalex.org/W2811079561","https://openalex.org/W2910577860","https://openalex.org/W2950547518","https://openalex.org/W2951928450","https://openalex.org/W2970006822","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W3097828251","https://openalex.org/W3160326269","https://openalex.org/W3162366763","https://openalex.org/W3196468212","https://openalex.org/W3214281017","https://openalex.org/W4297817572","https://openalex.org/W6631190155","https://openalex.org/W6633727632","https://openalex.org/W6657159850","https://openalex.org/W6732429163","https://openalex.org/W6743002019","https://openalex.org/W6753018729","https://openalex.org/W6753984127","https://openalex.org/W6755182157","https://openalex.org/W6755257315","https://openalex.org/W6758675244","https://openalex.org/W6767111847","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W2969399009"],"abstract_inverted_index":{"In":[0],"this":[1,45],"paper,":[2],"we":[3],"propose":[4],"a":[5,116],"discriminator":[6,27],"design":[7],"scheme":[8],"for":[9,90],"generative":[10],"adversarial":[11],"network-based":[12],"audio":[13,30,57,70],"signal":[14,23,31],"generation.":[15],"Unlike":[16],"conventional":[17,49],"discriminators":[18,50],"that":[19,48,100],"take":[20],"an":[21],"entire":[22],"as":[24],"input,":[25],"our":[26,72,101],"separates":[28],"the":[29,66,76,91,94,105],"into":[32],"harmonic":[33,81],"and":[34,37,82,109],"percussive":[35,83],"components":[36],"analyzes":[38],"each":[39],"component":[40],"independently.":[41],"The":[42],"rationale":[43],"behind":[44],"idea":[46],"is":[47],"cannot":[51],"reliably":[52],"capture":[53],"subtle":[54],"distortions":[55],"in":[56],"signals,":[58,71],"which":[59,87],"have":[60],"complicated":[61],"time-frequency":[62,67],"characteristics.":[63],"By":[64],"considering":[65],"resolution":[68],"of":[69,86,93,107],"proposed":[73],"method":[74],"encourages":[75],"generator":[77],"to":[78,115],"better":[79],"reconstruct":[80],"features,":[84],"both":[85],"are":[88],"critical":[89],"quality":[92],"generated":[95],"signals.":[96],"Listening":[97],"tests":[98],"show":[99],"framework":[102],"significantly":[103],"enhances":[104],"stability":[106],"pitches":[108],"generates":[110],"clearer":[111],"piano":[112],"samples":[113],"compared":[114],"baseline.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
