{"id":"https://openalex.org/W4414359564","doi":"https://doi.org/10.24963/ijcai.2025/1129","title":"SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning","display_name":"SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359564","doi":"https://doi.org/10.24963/ijcai.2025/1129"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1129","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5108466371","display_name":"Won Chul Shin","orcid":"https://orcid.org/0000-0003-3044-9397"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonchul Shin","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029123249","display_name":"Kyogu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27247007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10162","last_page":"10170"},"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/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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9986000061035156,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6039000153541565},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5763000249862671},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.567300021648407},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5224000215530396},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43869999051094055},{"id":"https://openalex.org/keywords/sound-reinforcement-system","display_name":"Sound reinforcement system","score":0.40639999508857727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246999740600586},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43869999051094055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424699991941452},{"id":"https://openalex.org/C30246029","wikidata":"https://www.wikidata.org/wiki/Q829504","display_name":"Sound reinforcement system","level":5,"score":0.40639999508857727},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2984030306","wikidata":"https://www.wikidata.org/wiki/Q4819857","display_name":"Sound analysis","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1129","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalization":[0],"of":[1,16,24,89,112,123],"synthesizer":[2,44],"sound":[3,17,45,49,124],"matching":[4],"to":[5,13,80],"external":[6],"instrument":[7],"sounds":[8,26],"is":[9],"highly":[10],"challenging":[11],"due":[12],"the":[14,22,52,86,90,110],"non-differentiability":[15],"synthesis":[18,30,58],"process":[19],"which":[20],"prohibits":[21],"use":[23],"out-of-domain":[25,66,104],"for":[27,42],"training":[28,83],"with":[29,120],"parameter":[31],"loss.":[32],"We":[33],"propose":[34],"SynthRL,":[35],"a":[36,71,117],"novel":[37],"reinforcement":[38],"learning":[39],"(RL)-based":[40],"approach":[41],"cross-domain":[43],"matching.":[46],"By":[47],"incorporating":[48],"similarity":[50],"into":[51],"reward":[53,114],"function,":[54],"SynthRL":[55,96],"effectively":[56],"optimizes":[57],"parameters":[59],"without":[60],"ground-truth":[61],"labels,":[62],"allowing":[63],"fine-tuning":[64],"on":[65,100],"sounds.":[67],"Furthermore,":[68],"we":[69],"introduce":[70],"transformer-based":[72],"model":[73],"architecture":[74],"and":[75,103],"reward-based":[76],"prioritized":[77],"experience":[78],"replay":[79],"enhance":[81],"RL":[82],"efficiency,":[84],"considering":[85],"unique":[87],"characteristics":[88],"task.":[91],"Experimental":[92],"results":[93],"demonstrate":[94],"that":[95],"outperforms":[97],"state-of-the-art":[98],"methods":[99],"both":[101],"in-domain":[102],"tasks.":[105],"Further":[106],"experimental":[107],"analysis":[108],"validates":[109],"effectiveness":[111],"our":[113],"design,":[115],"showing":[116],"strong":[118],"correlation":[119],"human":[121],"perception":[122],"similarity.":[125]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}