{"id":"https://openalex.org/W4392904177","doi":"https://doi.org/10.1109/icassp48485.2024.10446906","title":"Environmental Sound Synthesis from Vocal Imitations and Sound Event Labels","display_name":"Environmental Sound Synthesis from Vocal Imitations and Sound Event Labels","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904177","doi":"https://doi.org/10.1109/icassp48485.2024.10446906"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446906","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5113959532","display_name":"Yuki Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Okamoto","raw_affiliation_strings":["Ritsumeikan University,Japan","Ritsumeikan University, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Doshisha University,Japan","Doshisha University, Japan"],"affiliations":[{"raw_affiliation_string":"Doshisha University,Japan","institution_ids":["https://openalex.org/I133984924"]},{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001641384","display_name":"Ryotaro Nagase","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryotaro Nagase","raw_affiliation_strings":["Ritsumeikan University,Japan","Ritsumeikan University, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051293207","display_name":"Takahiro Fukumori","orcid":"https://orcid.org/0000-0002-4317-9704"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Fukumori","raw_affiliation_strings":["Ritsumeikan University,Japan","Ritsumeikan University, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103048025","display_name":"Yoichi Yamashita","orcid":"https://orcid.org/0000-0001-5379-9686"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Yamashita","raw_affiliation_strings":["Ritsumeikan University,Japan","Ritsumeikan University, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113959532"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.3415,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4791755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9993000030517578,"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":0.9973999857902527,"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/sound","display_name":"Sound (geography)","score":0.7565606236457825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6648200154304504},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.6261947154998779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.619973361492157},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6171244382858276},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.553766667842865},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10765501856803894}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7565606236457825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6648200154304504},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.6261947154998779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.619973361492157},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6171244382858276},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.553766667842865},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10765501856803894},{"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/icassp48485.2024.10446906","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/13","score":0.47999998927116394,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4047552544","display_name":"A study on environmental sound analysis based on unified and continual learning","funder_award_id":"23K16908","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6310141580","display_name":"\u3042\u3089\u3086\u308b\u97f3\u3092\u67d4\u8edf\u306b\u751f\u6210\u53ef\u80fd\u3068\u3059\u308b\u74b0\u5883\u97f3\u5408\u6210\u306e\u7814\u7a76","funder_award_id":"22KJ3027","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1969746716","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2055561493","https://openalex.org/W2167700723","https://openalex.org/W2593116425","https://openalex.org/W2771361008","https://openalex.org/W2890913619","https://openalex.org/W2935170919","https://openalex.org/W2963807156","https://openalex.org/W2964243274","https://openalex.org/W2964345931","https://openalex.org/W3007488268","https://openalex.org/W3046890131","https://openalex.org/W3127705815","https://openalex.org/W3214281017","https://openalex.org/W4205689591","https://openalex.org/W4310873011","https://openalex.org/W4318752004","https://openalex.org/W4360978942","https://openalex.org/W4367359628","https://openalex.org/W4372346311","https://openalex.org/W4385822330","https://openalex.org/W4394671563","https://openalex.org/W6767164110","https://openalex.org/W6790356757","https://openalex.org/W6845479124","https://openalex.org/W6849109464"],"related_works":["https://openalex.org/W2072492413","https://openalex.org/W2997159972","https://openalex.org/W4296378967","https://openalex.org/W2064134577","https://openalex.org/W2373995729","https://openalex.org/W3203096336","https://openalex.org/W2157038729","https://openalex.org/W2393707162","https://openalex.org/W2027715794","https://openalex.org/W2043981220"],"abstract_inverted_index":{"One":[0],"way":[1],"of":[2,15,23,33,88,108,135],"expressing":[3],"an":[4,61],"environmental":[5,34,62,74],"sound":[6,54,63,75,81,114],"is":[7,100],"using":[8,41],"vocal":[9,42,78,98,127],"imitations,":[10,43],"which":[11,44,112],"involve":[12],"the":[13,19,31,94,104,109,131],"process":[14],"replicating":[16],"or":[17,58],"mimicking":[18],"rhythm":[20,38,107,134],"and":[21,39,80,93,106,121,133],"pitch":[22,105,132],"sounds":[24],"by":[25,48],"voice.":[26],"We":[27],"can":[28],"effectively":[29,129],"express":[30],"features":[32],"sounds,":[35],"such":[36,52],"as":[37,53],"pitch,":[40],"cannot":[45,117],"be":[46],"expressed":[47],"conventional":[49],"input":[50],"information,":[51],"event":[55,82,115],"labels,":[56],"images,":[57],"texts,":[59],"in":[60],"synthesis":[64,76],"model.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"a":[71,86,89],"framework":[72,87],"for":[73],"from":[77],"imitations":[79,99,128],"labels":[83,116],"based":[84],"on":[85],"vector":[90],"quantized":[91],"encoder":[92],"Tacotron2":[95],"decoder.":[96],"Using":[97],"expected":[101],"to":[102],"control":[103,130],"synthesized":[110,136],"sound,":[111],"only":[113],"control.":[118],"Our":[119],"objective":[120],"subjective":[122],"experimental":[123],"results":[124],"show":[125],"that":[126],"sounds.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
