{"id":"https://openalex.org/W2899017552","doi":"https://doi.org/10.1109/icassp.2019.8683596","title":"Neural Music Synthesis for Flexible Timbre Control","display_name":"Neural Music Synthesis for Flexible Timbre Control","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2899017552","doi":"https://doi.org/10.1109/icassp.2019.8683596","mag":"2899017552"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.00223","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100726106","display_name":"Jong Wook Kim","orcid":"https://orcid.org/0000-0001-8373-1893"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jong Wook Kim","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019790225","display_name":"Rachel Bittner","orcid":"https://orcid.org/0000-0001-7757-2232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachel Bittner","raw_affiliation_strings":["Spotify"],"affiliations":[{"raw_affiliation_string":"Spotify","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111713058","display_name":"Aparna Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aparna Kumar","raw_affiliation_strings":["Spotify"],"affiliations":[{"raw_affiliation_string":"Spotify","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100726106"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00421297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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":0.9865999817848206,"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/timbre","display_name":"Timbre","score":0.9521121382713318},{"id":"https://openalex.org/keywords/morphing","display_name":"Morphing","score":0.8706669807434082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.70013427734375},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6832116842269897},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6383188962936401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5364573001861572},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.5211660861968994},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5076130628585815},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4686652421951294},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42082759737968445},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4170931875705719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32033050060272217},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.21223026514053345},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20953994989395142},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.14617395401000977}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9521121382713318},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.8706669807434082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70013427734375},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6832116842269897},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6383188962936401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5364573001861572},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.5211660861968994},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5076130628585815},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4686652421951294},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42082759737968445},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4170931875705719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32033050060272217},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.21223026514053345},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20953994989395142},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.14617395401000977},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.00223","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.00223","pdf_url":"https://arxiv.org/pdf/1811.00223","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.1811.00223","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.00223","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2899017552","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.00223","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.00223","pdf_url":"https://arxiv.org/pdf/1811.00223","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899017552.pdf","grobid_xml":"https://content.openalex.org/works/W2899017552.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W1540051238","https://openalex.org/W1959608418","https://openalex.org/W1986595194","https://openalex.org/W1990611383","https://openalex.org/W2008066450","https://openalex.org/W2013552725","https://openalex.org/W2029049232","https://openalex.org/W2079080230","https://openalex.org/W2110007838","https://openalex.org/W2150307531","https://openalex.org/W2187089797","https://openalex.org/W2219653521","https://openalex.org/W2341580134","https://openalex.org/W2396187157","https://openalex.org/W2606176153","https://openalex.org/W2766812927","https://openalex.org/W2769810959","https://openalex.org/W2803963372","https://openalex.org/W2804722844","https://openalex.org/W2898148140","https://openalex.org/W2949382160","https://openalex.org/W2963470893","https://openalex.org/W2963493667","https://openalex.org/W2963551352","https://openalex.org/W2963782041","https://openalex.org/W2963921132","https://openalex.org/W2964243274","https://openalex.org/W6600593648","https://openalex.org/W6632190515","https://openalex.org/W6640963894","https://openalex.org/W6704437622","https://openalex.org/W6712347974","https://openalex.org/W6730401039","https://openalex.org/W6736723571","https://openalex.org/W6740674931","https://openalex.org/W6745697700","https://openalex.org/W6745851314","https://openalex.org/W6751670691","https://openalex.org/W6752096078","https://openalex.org/W6861075418"],"related_works":["https://openalex.org/W2962721334","https://openalex.org/W2406877384","https://openalex.org/W3100781494","https://openalex.org/W2951535099","https://openalex.org/W2963889406","https://openalex.org/W2030392454","https://openalex.org/W2604509013","https://openalex.org/W3196783587","https://openalex.org/W3212416539","https://openalex.org/W2778460379","https://openalex.org/W1707503119","https://openalex.org/W2168076830","https://openalex.org/W3196700074","https://openalex.org/W49287718","https://openalex.org/W3186846710","https://openalex.org/W2993677600","https://openalex.org/W3197911684","https://openalex.org/W3098670224","https://openalex.org/W3203579625","https://openalex.org/W2198584637"],"abstract_inverted_index":{"The":[0,70,99],"recent":[1],"success":[2],"of":[3,54],"raw":[4],"audio":[5,25],"waveform":[6],"synthesis":[7,46,100],"models":[8],"like":[9],"WaveNet":[10,68],"motivates":[11],"a":[12,28,43,55,61,67,82],"new":[13],"approach":[14],"for":[15],"music":[16,45],"synthesis,":[17],"in":[18,79,95],"which":[19,52],"the":[20,76,96],"entire":[21],"process":[22],"-":[23,33],"creating":[24],"samples":[26],"from":[27],"score":[29],"and":[30,85,89,106,108],"instrument":[31,63],"information":[32],"is":[34,102,113],"modeled":[35],"using":[36],"generative":[37],"neural":[38,44,57],"networks.":[39],"This":[40],"paper":[41],"describes":[42],"model":[47],"with":[48],"flexible":[49],"timbre":[50,87],"controls,":[51],"consists":[53],"recurrent":[56],"network":[58],"conditioned":[59],"on":[60],"learned":[62,71],"embedding":[64,72,97],"followed":[65],"by":[66,91],"vocoder.":[69],"space":[73],"successfully":[74],"captures":[75],"diverse":[77],"variations":[78],"timbres":[80],"within":[81],"large":[83],"dataset":[84],"enables":[86],"control":[88],"morphing":[90],"interpolating":[92],"between":[93],"instruments":[94],"space.":[98],"quality":[101],"evaluated":[103],"both":[104],"numerically":[105],"perceptually,":[107],"an":[109],"interactive":[110],"web":[111],"demo":[112],"presented.":[114]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
