{"id":"https://openalex.org/W4285606794","doi":"https://doi.org/10.24963/ijcai.2022/682","title":"Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation","display_name":"Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606794","doi":"https://doi.org/10.24963/ijcai.2022/682"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/682","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/682","pdf_url":"https://www.ijcai.org/proceedings/2022/0682.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0682.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101718220","display_name":"Zui Chen","orcid":"https://orcid.org/0009-0008-3488-7312"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zui Chen","raw_affiliation_strings":["Tsinghua University","Institute for Interdisciplinary Information Sciences, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109580958","display_name":"Yansen Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansen Jing","raw_affiliation_strings":["Tsinghua University","Institute for Interdisciplinary Information Sciences, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068788728","display_name":"Shengcheng Yuan","orcid":"https://orcid.org/0000-0002-2540-5245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengcheng Yuan","raw_affiliation_strings":["Beijing DeepMusic Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing DeepMusic Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781351","display_name":"Yifei Xu","orcid":"https://orcid.org/0009-0009-2405-1113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Xu","raw_affiliation_strings":["Beijing DeepMusic Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing DeepMusic Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596094","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-9523-5237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Beijing DeepMusic Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing DeepMusic Technology Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101826600","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0002-8690-415X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Tsinghua University","Institute for Interdisciplinary Information Sciences, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4921","last_page":"4928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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/timbre","display_name":"Timbre","score":0.8939458131790161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7021057605743408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5112147331237793},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4757556617259979},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4751025438308716},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47132328152656555},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4590538740158081},{"id":"https://openalex.org/keywords/frequency-synthesizer","display_name":"Frequency synthesizer","score":0.45340341329574585},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4454284906387329},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.33646753430366516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2283739149570465},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2114042341709137},{"id":"https://openalex.org/keywords/phase-locked-loop","display_name":"Phase-locked loop","score":0.14884886145591736},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11461740732192993},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09381496906280518},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0821530818939209},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.08002170920372009}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8939458131790161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021057605743408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5112147331237793},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4757556617259979},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4751025438308716},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47132328152656555},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4590538740158081},{"id":"https://openalex.org/C182099602","wikidata":"https://www.wikidata.org/wiki/Q2660678","display_name":"Frequency synthesizer","level":4,"score":0.45340341329574585},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4454284906387329},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.33646753430366516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2283739149570465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2114042341709137},{"id":"https://openalex.org/C12707504","wikidata":"https://www.wikidata.org/wiki/Q52637","display_name":"Phase-locked loop","level":3,"score":0.14884886145591736},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11461740732192993},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09381496906280518},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0821530818939209},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.08002170920372009},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/682","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/682","pdf_url":"https://www.ijcai.org/proceedings/2022/0682.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.03043","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.03043","pdf_url":"https://arxiv.org/pdf/2205.03043","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/682","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/682","pdf_url":"https://www.ijcai.org/proceedings/2022/0682.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606794.pdf","grobid_xml":"https://content.openalex.org/works/W4285606794.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1541986262","https://openalex.org/W1686810756","https://openalex.org/W1949442742","https://openalex.org/W1998446618","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2392029795","https://openalex.org/W2791716806","https://openalex.org/W2905015588","https://openalex.org/W2908510526","https://openalex.org/W2955263139","https://openalex.org/W2963446712","https://openalex.org/W3000389243","https://openalex.org/W3158390048","https://openalex.org/W4285367200"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299"],"abstract_inverted_index":{"Synthesizer":[0],"is":[1,9,53],"a":[2,24,27,35,42,50,67,74,102],"type":[3],"of":[4,23,40,44],"electronic":[5],"musical":[6],"instrument":[7],"that":[8,47],"now":[10],"widely":[11],"used":[12],"in":[13],"modern":[14],"music":[15],"production":[16],"and":[17,30],"sound":[18,51],"design.":[19],"Each":[20],"parameters":[21,45,62],"configuration":[22,46],"synthesizer":[25,61],"produces":[26],"unique":[28,36],"timbre":[29,52],"can":[31],"be":[32],"viewed":[33],"as":[34],"instrument.":[37],"The":[38],"problem":[39],"estimating":[41],"set":[43],"best":[48],"restore":[49],"an":[54],"important":[55],"yet":[56],"complicated":[57],"problem,":[58],"i.e.:":[59],"the":[60,94],"estimation":[63],"problem.":[64,85],"We":[65],"proposed":[66],"multi-modal":[68],"deep-learning-based":[69],"pipeline":[70],"Sound2Synth,":[71],"together":[72],"with":[73],"network":[75],"structure":[76],"Prime-Dilated":[77],"Convolution":[78],"(PDC)":[79],"specially":[80],"designed":[81],"to":[82],"solve":[83],"this":[84],"Our":[86],"method":[87],"achieved":[88],"not":[89],"only":[90],"SOTA":[91],"but":[92],"also":[93],"first":[95],"real-world":[96],"applicable":[97],"results":[98],"on":[99],"Dexed":[100],"synthesizer,":[101],"popular":[103],"FM":[104],"synthesizer.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}