{"id":"https://openalex.org/W4392904621","doi":"https://doi.org/10.1109/icassp48485.2024.10446678","title":"Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting","display_name":"Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904621","doi":"https://doi.org/10.1109/icassp48485.2024.10446678"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446678","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/A5033570183","display_name":"Hounsu Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hounsu Kim","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102743910","display_name":"Soonbeom Choi","orcid":"https://orcid.org/0000-0002-4446-6174"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonbeom Choi","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033570183"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.5001,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80747403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7620","last_page":"7624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.9392157793045044},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8395580649375916},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.7892841100692749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820502519607544},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7115904092788696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.58855801820755},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5222212076187134},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48741820454597473},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2421203851699829},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09364596009254456}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.9392157793045044},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8395580649375916},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7892841100692749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820502519607544},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7115904092788696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.58855801820755},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5222212076187134},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48741820454597473},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2421203851699829},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09364596009254456},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446678","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2120918099","https://openalex.org/W2526050071","https://openalex.org/W2606176153","https://openalex.org/W2899724567","https://openalex.org/W2902076983","https://openalex.org/W2910577860","https://openalex.org/W2962721334","https://openalex.org/W2972478942","https://openalex.org/W2998490864","https://openalex.org/W3036167779","https://openalex.org/W3094550259","https://openalex.org/W3110257065","https://openalex.org/W3215615641","https://openalex.org/W4221145412","https://openalex.org/W4225716783","https://openalex.org/W4225759859","https://openalex.org/W4281872541","https://openalex.org/W4282913091","https://openalex.org/W4288089799","https://openalex.org/W4297772864","https://openalex.org/W4312497550","https://openalex.org/W4322615164","https://openalex.org/W4372341951","https://openalex.org/W6600901058","https://openalex.org/W6691096134","https://openalex.org/W6717434760","https://openalex.org/W6721020019","https://openalex.org/W6736723571","https://openalex.org/W6754333143","https://openalex.org/W6756341328","https://openalex.org/W6758675244","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6803088475","https://openalex.org/W6809940947","https://openalex.org/W6810708459","https://openalex.org/W6838452192","https://openalex.org/W6839052650","https://openalex.org/W6839133533","https://openalex.org/W6840815571"],"related_works":["https://openalex.org/W1564064486","https://openalex.org/W2153331925","https://openalex.org/W2992982157","https://openalex.org/W4375868955","https://openalex.org/W2369521057","https://openalex.org/W3137927517","https://openalex.org/W2040048036","https://openalex.org/W2607529793","https://openalex.org/W2978163245","https://openalex.org/W3033263360"],"abstract_inverted_index":{"Synthesizing":[0],"performing":[1],"guitar":[2,49,93,104],"sound":[3,50],"is":[4],"a":[5,37,54,100],"highly":[6],"challenging":[7],"task":[8],"due":[9],"to":[10,58],"the":[11,59,67,82,122,132],"polyphony":[12],"and":[13,108,125],"high":[14,101],"variability":[15],"in":[16,26],"expression.":[17],"Recently,":[18],"deep":[19],"generative":[20],"models":[21],"have":[22],"shown":[23],"promising":[24],"results":[25],"synthesizing":[27],"expressive":[28,47],"polyphonic":[29],"instrument":[30],"sounds":[31,130],"from":[32,99],"music":[33],"scores,":[34],"often":[35],"using":[36,70],"generic":[38],"MIDI":[39],"input.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,62,87,111],"propose":[45],"an":[46,91],"acoustic":[48],"synthesis":[51],"model":[52,116,124],"with":[53,77],"customized":[55],"input":[56],"representation":[57],"instrument,":[60],"which":[61,73],"call":[63],"guitarroll.":[64],"We":[65],"implement":[66],"proposed":[68,115],"approach":[69],"diffusion-based":[71],"outpainting":[72],"can":[74],"generate":[75],"audio":[76,119],"long-term":[78],"consistency.":[79],"To":[80],"overcome":[81],"lack":[83],"of":[84],"MIDI/audio-paired":[85],"datasets,":[86],"used":[88],"not":[89],"only":[90],"existing":[92],"dataset":[94],"but":[95],"also":[96],"collected":[97],"data":[98],"quality":[102,120],"sample-based":[103],"synthesizer.":[105],"Through":[106],"quantitative":[107],"qualitative":[109],"evaluations,":[110],"show":[112],"that":[113],"our":[114],"has":[117],"higher":[118],"than":[121,131],"baseline":[123],"generates":[126],"more":[127],"realistic":[128],"timbre":[129],"previous":[133],"leading":[134],"work.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}