{"id":"https://openalex.org/W7127054745","doi":"https://doi.org/10.1145/3784833.3784908","title":"Scalable Synthetic Data Pipeline and End-to-End Sound Synthesis: A Case Study on the Chinese Dizi","display_name":"Scalable Synthetic Data Pipeline and End-to-End Sound Synthesis: A Case Study on the Chinese Dizi","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7127054745","doi":"https://doi.org/10.1145/3784833.3784908"},"language":null,"primary_location":{"id":"doi:10.1145/3784833.3784908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784908","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784833.3784908","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124716782","display_name":"Junchen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchen Liu","raw_affiliation_strings":["Hainan Advanced Digital Technology and Systems Laboratory, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0743-4418","affiliations":[{"raw_affiliation_string":"Hainan Advanced Digital Technology and Systems Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124747660","display_name":"Rongfeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongfeng Li","raw_affiliation_strings":["Hainan Advanced Digital Technology and Systems Laboratory, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5595-3701","affiliations":[{"raw_affiliation_string":"Hainan Advanced Digital Technology and Systems Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124702810","display_name":"Zijin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2799899675","display_name":"Central Conservatory of Music","ror":"https://ror.org/01pxc4g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799899675"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijin Li","raw_affiliation_strings":["Central Conservatory of Music, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2052-3472","affiliations":[{"raw_affiliation_string":"Central Conservatory of Music, Beijing, China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124724043","display_name":"Ya Li","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Music College, Shanghai Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-9763-965X","affiliations":[{"raw_affiliation_string":"Music College, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124748855","display_name":"Linfeng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799899675","display_name":"Central Conservatory of Music","ror":"https://ror.org/01pxc4g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799899675"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linfeng Fan","raw_affiliation_strings":["Central Conservatory of Music, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3952-1742","affiliations":[{"raw_affiliation_string":"Central Conservatory of Music, Beijing, China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124746995","display_name":"Pei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Huang","raw_affiliation_strings":["School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-1352-3441","affiliations":[{"raw_affiliation_string":"School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7705000042915344,"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":0.7705000042915344,"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":0.1891999989748001,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.006300000008195639,"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":0.8183000087738037},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7804999947547913},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6007999777793884},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.4828999936580658},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.46799999475479126},{"id":"https://openalex.org/keywords/flute","display_name":"Flute","score":0.44449999928474426},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3970000147819519},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.3869999945163727},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.37439998984336853}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8183000087738037},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7804999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808000206947327},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C4060165","wikidata":"https://www.wikidata.org/wiki/Q11405","display_name":"Flute","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3398999869823456},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C499572226","wikidata":"https://www.wikidata.org/wiki/Q1937950","display_name":"Sound design","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.29910001158714294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C178884764","wikidata":"https://www.wikidata.org/wiki/Q510293","display_name":"Musical acoustics","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784833.3784908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784908","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3784833.3784908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784908","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6249449253082275,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1558402437","https://openalex.org/W2583147637","https://openalex.org/W2742634874","https://openalex.org/W2759171953","https://openalex.org/W3015338123","https://openalex.org/W4298188388","https://openalex.org/W4360612734","https://openalex.org/W4392903114","https://openalex.org/W4404075137","https://openalex.org/W4408542701","https://openalex.org/W4415797489"],"related_works":[],"abstract_inverted_index":{"Many":[0],"musical":[1],"instruments":[2,27],"across":[3],"cultures":[4],"remain":[5],"underrepresented":[6,89],"in":[7],"digital":[8,153],"media":[9],"due":[10],"to":[11,102,132],"limited":[12],"data":[13,69,141],"availability":[14],"and":[15,24,43,99,106,155,160],"the":[16,109,122,129,134],"high":[17],"cost":[18],"of":[19,82,124,136,158],"collecting":[20],"high-quality":[21],"recordings.":[22],"Modeling":[23],"synthesizing":[25],"these":[26],"are":[28],"crucial":[29],"not":[30],"only":[31],"for":[32,38,88,145,152],"music":[33,45],"technology":[34],"research":[35],"but":[36],"also":[37],"cultural":[39],"preservation,":[40],"creative":[41],"accessibility,":[42],"intelligent":[44],"design.":[46],"A":[47],"promising":[48],"approach":[49],"is":[50],"symbolic-to-audio":[51],"synthesis,":[52],"which":[53],"generates":[54],"realistic":[55],"sounds":[56],"directly":[57],"from":[58],"symbolic":[59],"representations":[60],"such":[61],"as":[62,116],"MIDI,":[63],"yet":[64],"current":[65],"methods":[66],"struggle":[67],"with":[68],"scarcity.":[70],"To":[71],"address":[72],"this":[73],"issue,":[74],"we":[75,120],"present":[76],"a":[77,117,149],"scalable":[78],"data-generation":[79],"pipeline":[80,92,126],"capable":[81],"producing":[83],"adequate":[84],"paired":[85],"MIDI\u2014Audio":[86],"samples":[87],"instruments.":[90,162],"The":[91],"integrates":[93],"rule-based":[94],"score":[95],"construction,":[96],"automated":[97],"rendering,":[98],"feature":[100],"extraction":[101],"ensure":[103],"both":[104],"fidelity":[105],"diversity.":[107],"Using":[108],"Chinese":[110],"bamboo":[111],"flute":[112],"(dizi,":[113],"or":[114],"qudi)":[115],"case":[118],"study,":[119],"demonstrate":[121],"practicality":[123],"our":[125],"by":[127],"reproducing":[128],"MIDI-DDSP":[130],"experiment":[131],"validate":[133],"usability":[135],"its":[137],"synthetic":[138],"data.":[139],"Synthetic":[140],"provides":[142],"robust":[143],"coverage":[144],"timbre":[146],"modeling,":[147],"contributing":[148],"high-fidelity":[150],"system":[151],"modeling":[154],"information":[156],"processing":[157],"minority":[159],"traditional":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-03T00:00:00"}
