{"id":"https://openalex.org/W2965526162","doi":"https://doi.org/10.24963/ijcai.2019/467","title":"SynthNet: Learning to Synthesize Music End-to-End","display_name":"SynthNet: Learning to Synthesize Music End-to-End","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965526162","doi":"https://doi.org/10.24963/ijcai.2019/467","mag":"2965526162"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/467","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/467","pdf_url":"https://www.ijcai.org/proceedings/2019/0467.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0467.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054885916","display_name":"Florin Schimbinschi","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Florin Schimbinschi","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063357214","display_name":"Christian Walder","orcid":"https://orcid.org/0000-0002-2411-3523"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christian Walder","raw_affiliation_strings":["Data61 CSIRO Australian National University","Data61 CSIRO, Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61 CSIRO Australian National University","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I42894916"]},{"raw_affiliation_string":"Data61 CSIRO, Australian National University","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070030398","display_name":"Sarah Erfani","orcid":"https://orcid.org/0000-0003-0885-0643"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarah M. Erfani","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101609697","display_name":"James Bailey","orcid":"https://orcid.org/0000-0002-3769-3811"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"James Bailey","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3367","last_page":"3374"},"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":0.9994000196456909,"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":0.998199999332428,"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/timbre","display_name":"Timbre","score":0.7609536647796631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598481178283691},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5527700781822205},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5511007308959961},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4637508988380432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4412972331047058},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.44082021713256836},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4365490972995758},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.43504905700683594},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.42335838079452515},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3693992793560028},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.31404849886894226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1376371681690216},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11771270632743835}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7609536647796631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598481178283691},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5527700781822205},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5511007308959961},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4637508988380432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4412972331047058},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.44082021713256836},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4365490972995758},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.43504905700683594},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.42335838079452515},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3693992793560028},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31404849886894226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1376371681690216},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11771270632743835},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/467","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/467","pdf_url":"https://www.ijcai.org/proceedings/2019/0467.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/467","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/467","pdf_url":"https://www.ijcai.org/proceedings/2019/0467.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320386","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965526162.pdf","grobid_xml":"https://content.openalex.org/works/W2965526162.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2076608692","https://openalex.org/W2099057450","https://openalex.org/W2187089797","https://openalex.org/W2519091744","https://openalex.org/W2531409750","https://openalex.org/W2559688696","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2606176153","https://openalex.org/W2612445135","https://openalex.org/W2752134738","https://openalex.org/W2786254735","https://openalex.org/W2811079561","https://openalex.org/W2949382160","https://openalex.org/W2963233633","https://openalex.org/W2963454111","https://openalex.org/W2963920537","https://openalex.org/W4297775537","https://openalex.org/W4298366219"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W4310670065","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580","https://openalex.org/W2352995288","https://openalex.org/W2365365224","https://openalex.org/W2509206472"],"abstract_inverted_index":{"We":[0,19,37],"consider":[1],"the":[2,39,54,62,67,98,108,121,129,132],"problem":[3],"of":[4,100,107,131],"learning":[5],"a":[6,21,27],"mapping":[7],"directly":[8,60],"from":[9,61,139],"annotated":[10],"music":[11,46,153],"to":[12,35,94,103,120,160],"waveforms,":[13],"bypassing":[14],"traditional":[15],"single":[16],"note":[17],"synthesis.":[18],"propose":[20],"specific":[22],"architecture":[23],"based":[24,126],"on":[25,45,127],"WaveNet,":[26],"convolutional":[28],"autoregressive":[29],"generative":[30],"model":[31,75],"designed":[32],"for":[33],"text":[34,102],"speech.":[36],"investigate":[38],"representations":[40],"learned":[41,59],"by":[42],"these":[43],"models":[44],"and":[47,53,87,135,154,158],"concludethat":[48],"mappings":[49],"between":[50],"musical":[51,68],"notes":[52],"instrument":[55,149],"timbre":[56],"can":[57],"be":[58],"raw":[63],"audio":[64],"coupled":[65],"with":[66],"score,":[69],"in":[70,85,92,97],"binary":[71],"piano":[72],"roll":[73],"format.Our":[74],"requires":[76],"minimal":[77],"training":[78],"data":[79],"(9":[80],"minutes),":[81],"is":[82,113],"substantially":[83],"better":[84],"quality":[86,106],"converges":[88],"6":[89],"times":[90],"faster":[91],"comparison":[93],"strong":[95],"baselines":[96],"form":[99],"powerful":[101],"speech":[104],"models.The":[105],"generated":[109,162],"waveforms":[110],"(generation":[111],"accuracy)":[112],"sufficiently":[114],"high,that":[115],"they":[116],"are":[117,125],"almost":[118],"identical":[119],"ground":[122],"truth.Our":[123],"evaluations":[124],"both":[128],"RMSE":[130],"Constant-Q":[133],"transform,":[134],"mean":[136],"opinion":[137],"scores":[138],"human":[140],"subjects.We":[141],"validate":[142],"our":[143],"work":[144],"using":[145],"7":[146],"distinct":[147],"synthetic":[148],"timbres,":[150],"real":[151],"cello":[152],"also":[155],"provide":[156],"visualizations":[157],"links":[159],"all":[161],"audio.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}