{"id":"https://openalex.org/W7204493792","doi":"https://doi.org/10.1108/atsip-02-2026-0010","title":"Sound effect synthesis from language-independent mimicry: a case study on explosion sounds","display_name":"Sound effect synthesis from language-independent mimicry: a case study on explosion sounds","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204493792","doi":"https://doi.org/10.1108/atsip-02-2026-0010"},"language":"en","primary_location":{"id":"doi:10.1108/atsip-02-2026-0010","doi":"https://doi.org/10.1108/atsip-02-2026-0010","is_oa":true,"landing_page_url":"https://doi.org/10.1108/atsip-02-2026-0010","pdf_url":"https://www.emerald.com/atsip/article-pdf/15/1/464/11811893/atsip-02-2026-0010en.pdf","source":{"id":"https://openalex.org/S4210170298","display_name":"APSIPA Transactions on Signal and Information Processing","issn_l":"2048-7703","issn":["2048-7703"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APSIPA Transactions on Signal and Information Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.emerald.com/atsip/article-pdf/15/1/464/11811893/atsip-02-2026-0010en.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080773720","display_name":"Riki Takizawa","orcid":"https://orcid.org/0000-0001-5724-5349","observed_orcids":["https://orcid.org/0000-0001-5724-5349"]},"institutions":[{"id":"https://openalex.org/I168356945","display_name":"Kyoto Sangyo University","ror":"https://ror.org/05t70xh16","country_code":"JP","type":"education","lineage":["https://openalex.org/I168356945"]},{"id":"https://openalex.org/I4405268240","display_name":"Artificial Intelligence Research Center","ror":"https://ror.org/009x1ke56","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4405268240"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Riki Takizawa","raw_affiliation_strings":["Kyoto Sangyo University Department of Frontier Informatics, , Kyoto,","National Institute of Advanced Industrial Science and Technology (AIST) Artificial Intelligence Research Center, , Tokyo,"],"raw_orcid":"https://orcid.org/0000-0001-5724-5349","affiliations":[{"raw_affiliation_string":"Kyoto Sangyo University Department of Frontier Informatics, , Kyoto,","institution_ids":["https://openalex.org/I168356945"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST) Artificial Intelligence Research Center, , Tokyo,","institution_ids":["https://openalex.org/I4405268240","https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050359918","display_name":"Shigeyuki Hirai","orcid":"https://orcid.org/0000-0003-2601-7903","observed_orcids":["https://orcid.org/0000-0003-2601-7903"]},"institutions":[{"id":"https://openalex.org/I168356945","display_name":"Kyoto Sangyo University","ror":"https://ror.org/05t70xh16","country_code":"JP","type":"education","lineage":["https://openalex.org/I168356945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeyuki Hirai","raw_affiliation_strings":["Kyoto Sangyo University Faculty of Information Science and Engineering, , Kyoto,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto Sangyo University Faculty of Information Science and Engineering, , Kyoto,","institution_ids":["https://openalex.org/I168356945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045505869","display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405","observed_orcids":["https://orcid.org/0000-0003-3217-1405"]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["Institute of Science Tokyo School of Computing, , Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo School of Computing, , Tokyo,","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008138836","display_name":"Hitoshi Suda","orcid":"https://orcid.org/0000-0003-2648-363X","observed_orcids":["https://orcid.org/0000-0003-2648-363X"]},"institutions":[{"id":"https://openalex.org/I4405268240","display_name":"Artificial Intelligence Research Center","ror":"https://ror.org/009x1ke56","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4405268240"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Suda","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST) Artificial Intelligence Research Center, , Tokyo,"],"raw_orcid":"https://orcid.org/0000-0003-2648-363X","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST) Artificial Intelligence Research Center, , Tokyo,","institution_ids":["https://openalex.org/I4405268240","https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080773720"],"corresponding_institution_ids":["https://openalex.org/I168356945","https://openalex.org/I4405268240","https://openalex.org/I73613424"],"apc_list":{"value":1000,"currency":"USD","value_usd":1000},"apc_paid":{"value":1000,"currency":"USD","value_usd":1000},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67751122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"1","first_page":"464","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.49410000443458557,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.49410000443458557,"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/T11309","display_name":"Music and Audio Processing","score":0.3384000062942505,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.08550000190734863,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/vocal-mimicry","display_name":"vocal mimicry","score":0.8980000019073486},{"id":"https://openalex.org/keywords/spectral-correspondence","display_name":"spectral correspondence","score":0.7639999985694885}],"concepts":[{"id":"https://openalex.org/C7863114","wikidata":"https://www.wikidata.org/wiki/Q192627","display_name":"Mimicry","level":2,"score":0.892799973487854},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.8083000183105469},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6079000234603882},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5303000211715698},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5012000203132629},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/atsip-02-2026-0010","doi":"https://doi.org/10.1108/atsip-02-2026-0010","is_oa":true,"landing_page_url":"https://doi.org/10.1108/atsip-02-2026-0010","pdf_url":"https://www.emerald.com/atsip/article-pdf/15/1/464/11811893/atsip-02-2026-0010en.pdf","source":{"id":"https://openalex.org/S4210170298","display_name":"APSIPA Transactions on Signal and Information Processing","issn_l":"2048-7703","issn":["2048-7703"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APSIPA Transactions on Signal and Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1108/atsip-02-2026-0010","doi":"https://doi.org/10.1108/atsip-02-2026-0010","is_oa":true,"landing_page_url":"https://doi.org/10.1108/atsip-02-2026-0010","pdf_url":"https://www.emerald.com/atsip/article-pdf/15/1/464/11811893/atsip-02-2026-0010en.pdf","source":{"id":"https://openalex.org/S4210170298","display_name":"APSIPA Transactions on Signal and Information Processing","issn_l":"2048-7703","issn":["2048-7703"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APSIPA Transactions on Signal and Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5398857593536377,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204493792.pdf","grobid_xml":"https://content.openalex.org/works/W7204493792.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2052900576","https://openalex.org/W2167700723","https://openalex.org/W2328666005","https://openalex.org/W2587787604","https://openalex.org/W2903739847","https://openalex.org/W2911954775","https://openalex.org/W2964243274","https://openalex.org/W2972478942","https://openalex.org/W3028131395","https://openalex.org/W3094550259","https://openalex.org/W4251818031","https://openalex.org/W4298711387","https://openalex.org/W4310873011","https://openalex.org/W4367359628","https://openalex.org/W4386071828","https://openalex.org/W4392903391","https://openalex.org/W4392904177","https://openalex.org/W4392910528","https://openalex.org/W4393487958","https://openalex.org/W4393671091","https://openalex.org/W4396877837","https://openalex.org/W4400579243","https://openalex.org/W4403763872","https://openalex.org/W4408352247","https://openalex.org/W4413144830","https://openalex.org/W6892605619"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"vocal-imitation-based":[1],"methods":[2],"for":[3,48,161],"environmental":[4],"sound":[5,7,49,67,140,199],"or":[6,16],"effect":[8,50,200],"synthesis":[9,131],"typically":[10],"use":[11],"root-mean-square":[12],"envelopes,":[13],"text":[14],"prompts":[15],"discrete":[17],"codes,":[18],"and":[19,28,66,106,124,141,153,163,182,191],"do":[20],"not":[21],"directly":[22,59],"learn":[23],"spectral":[24,61],"correspondences":[25,62],"between":[26,63],"imitation":[27,37],"target":[29,139],"sounds.":[30],"This":[31,52],"study":[32,53,83,128],"uses":[33],"vocal":[34,64,111,144],"mimicry,":[35],"nonlinguistic":[36],"produced":[38],"by":[39,179],"the":[40,75,138,186],"human":[41],"articulatory":[42],"system,":[43],"as":[44,95,194],"a":[45,56,85,96],"control":[46],"signal":[47],"synthesis.":[51,201],"proposes":[54],"PronounSE,":[55],"method":[57],"that":[58,165,174],"learns":[60],"mimicry":[65,76,112,145,169,180],"effects":[68],"to":[69,110,114,122,137],"generate":[70],"outputs":[71],"whose":[72],"nuances":[73],"follow":[74],"input.":[77],"To":[78],"address":[79],"data":[80,89],"scarcity,":[81],"this":[82,100,127],"constructs":[84],"new":[86],"paired":[87],"vocal-mimicry":[88],"set":[90],"focused":[91],"on":[92],"explosion":[93],"sounds":[94],"case":[97],"study,":[98],"since":[99],"category":[101],"exhibits":[102],"diverse":[103],"acoustic":[104],"variations":[105],"is":[107,176],"relatively":[108],"amenable":[109],"due":[113],"its":[115],"predominantly":[116],"aperiodic,":[117],"noise-like":[118],"characteristics.":[119],"In":[120],"addition":[121],"naturalness":[123],"audio":[125],"quality,":[126],"evaluates":[129],"mimicry-driven":[130],"with":[132],"two":[133],"task-specific":[134],"criteria:":[135],"fidelity":[136,162,175,190],"reflection":[142,193],"of":[143,188],"nuances.":[146,170],"These":[147],"four":[148],"criteria":[149,196],"support":[150],"both":[151],"objective":[152],"subjective":[154],"evaluation.":[155],"Results":[156,171],"show":[157],"strong":[158],"objective-subjective":[159],"correlations":[160],"confirm":[164],"PronounSE":[166],"effectively":[167],"reflects":[168],"also":[172],"indicate":[173],"strongly":[177],"affected":[178],"skill":[181],"speaker-specific":[183],"characteristics,":[184],"highlighting":[185],"importance":[187],"evaluating":[189],"nuance":[192],"distinct":[195],"in":[197],"vocal-mimicry-based":[198]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2026-08-28T00:00:00"}
