{"id":"https://openalex.org/W4387543562","doi":"https://doi.org/10.1145/3616195.3616221","title":"A Plugin for Neural Audio Synthesis of Impact Sound Effects","display_name":"A Plugin for Neural Audio Synthesis of Impact Sound Effects","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4387543562","doi":"https://doi.org/10.1145/3616195.3616221"},"language":"en","primary_location":{"id":"doi:10.1145/3616195.3616221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616195.3616221","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616221","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616221","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007530512","display_name":"Zih\u2010Syuan Yang","orcid":"https://orcid.org/0009-0007-0028-8437"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zih-Syuan Yang","raw_affiliation_strings":["Sound and Music Analysis Group, Digital Media Technology Lab, School of Computing and Digital Technology, Birmingham City University, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0007-0028-8437","affiliations":[{"raw_affiliation_string":"Sound and Music Analysis Group, Digital Media Technology Lab, School of Computing and Digital Technology, Birmingham City University, United Kingdom","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084229427","display_name":"Jason Hockman","orcid":"https://orcid.org/0000-0002-2911-6993"},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jason Hockman","raw_affiliation_strings":["School of Digital Arts (SODA), Manchester Metropolitan University, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2911-6993","affiliations":[{"raw_affiliation_string":"School of Digital Arts (SODA), Manchester Metropolitan University, United Kingdom","institution_ids":["https://openalex.org/I11983389"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007530512"],"corresponding_institution_ids":["https://openalex.org/I12870472"],"apc_list":null,"apc_paid":null,"fwci":0.3838,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57177344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7611583471298218},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5866946578025818},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5544509291648865},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5315007567405701},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5278042554855347},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4955817461013794},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.49357783794403076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48923468589782715},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.44845694303512573},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.44798049330711365},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4472556412220001},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44410914182662964},{"id":"https://openalex.org/keywords/surround-sound","display_name":"Surround sound","score":0.4221354126930237},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.340162992477417},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2743290066719055},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.26807230710983276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20528140664100647},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10726669430732727},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08044591546058655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611583471298218},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5866946578025818},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5544509291648865},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5315007567405701},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5278042554855347},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4955817461013794},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.49357783794403076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48923468589782715},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.44845694303512573},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.44798049330711365},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4472556412220001},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44410914182662964},{"id":"https://openalex.org/C2780544925","wikidata":"https://www.wikidata.org/wiki/Q569874","display_name":"Surround sound","level":3,"score":0.4221354126930237},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.340162992477417},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2743290066719055},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.26807230710983276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20528140664100647},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10726669430732727},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08044591546058655},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3616195.3616221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616195.3616221","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616221","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:e-space.mmu.ac.uk:633023","is_oa":true,"landing_page_url":"https://e-space.mmu.ac.uk/view/authors/0dd1c19d51a520c298190e299cc94cca.html>","pdf_url":"https://e-space.mmu.ac.uk/633023/1/am23_26.pdf","source":{"id":"https://openalex.org/S4306401617","display_name":"e-space (Manchester Metropolitan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11983389","host_organization_name":"Manchester Metropolitan University","host_organization_lineage":["https://openalex.org/I11983389"],"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":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1145/3616195.3616221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616195.3616221","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616221","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387543562.pdf","grobid_xml":"https://content.openalex.org/works/W4387543562.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1607348601","https://openalex.org/W2188043701","https://openalex.org/W2964121744","https://openalex.org/W4226317937","https://openalex.org/W4243637566","https://openalex.org/W4309117899"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W1975359510","https://openalex.org/W2056234363","https://openalex.org/W1496727373","https://openalex.org/W2020952589","https://openalex.org/W2970176078","https://openalex.org/W1526651343","https://openalex.org/W1590604789","https://openalex.org/W2088690926","https://openalex.org/W2155527258"],"abstract_inverted_index":{"The":[0,79,116,138],"term":[1],"impact":[2,65,98],"sound":[3,32,66,99],"as":[4,14,74,113],"referred":[5],"to":[6],"in":[7,36,49,71,103],"this":[8,136,143],"paper,":[9],"can":[10],"be":[11],"broadly":[12],"defined":[13],"the":[15,24,56,119,131],"sudden":[16],"burst":[17],"of":[18,26,31,42,58,95,118,135,142],"short-lasting":[19],"impulsive":[20],"noise":[21],"generated":[22],"by":[23],"collision":[25],"two":[27],"objects.":[28],"This":[29,53],"type":[30],"effect":[33],"is":[34,122],"prevalent":[35],"multimedia":[37,72],"productions.":[38],"However,":[39],"conventional":[40],"methods":[41],"sourcing":[43],"these":[44],"materials":[45],"are":[46,145],"often":[47],"costly":[48],"time":[50],"and":[51,77,133,140,150],"resources.":[52],"paper":[54,144],"explores":[55],"potential":[57],"neural":[59],"audio":[60,148],"synthesis":[61],"for":[62,69,101],"generating":[63],"realistic":[64],"effects,":[67],"targeted":[68],"use":[70],"such":[73],"films,":[75],"games,":[76],"AR/VR.":[78],"designed":[80],"system":[81],"uses":[82],"a":[83,93,104],"Realtime":[84],"Audio":[85,106],"Variational":[86],"autoEncoder":[87],"(RAVE)":[88],"[2]":[89],"model":[90,121],"trained":[91,120],"on":[92],"dataset":[94],"over":[96],"3,000":[97],"samples":[100],"inference":[102],"Digital":[105],"Workstation":[107],"(DAW),":[108],"with":[109,147],"latent":[110],"representations":[111],"exposed":[112],"user":[114],"controls.":[115],"performance":[117],"assessed":[123],"using":[124],"various":[125],"objective":[126],"evaluation":[127],"metrics,":[128],"revealing":[129],"both":[130],"prospects":[132],"limitations":[134],"approach.":[137],"results":[139],"contributions":[141],"discussed,":[146],"examples":[149],"source":[151],"code":[152],"made":[153],"available.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}