{"id":"https://openalex.org/W4392904237","doi":"https://doi.org/10.1109/icassp48485.2024.10446088","title":"STEMGEN: A Music Generation Model That Listens","display_name":"STEMGEN: A Music Generation Model That Listens","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904237","doi":"https://doi.org/10.1109/icassp48485.2024.10446088"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446088","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":"conference-paper","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/A5034175373","display_name":"Julian D. Parker","orcid":null},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Julian D. Parker","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005240622","display_name":"Janne Spijkervet","orcid":null},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Janne Spijkervet","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022096223","display_name":"Katerina Kosta","orcid":null},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Katerina Kosta","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103272931","display_name":"Furkan Yesiler","orcid":"https://orcid.org/0000-0002-6356-4853"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Furkan Yesiler","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064830223","display_name":"\u0411\u043e\u0440\u0438\u0441 \u041d. \u041a\u0443\u0437\u043d\u0435\u0446\u043e\u0432","orcid":"https://orcid.org/0000-0001-6309-6482"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Boris Kuznetsov","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089615767","display_name":"Matt Avent","orcid":null},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Matt Avent","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101809399","display_name":"Duc Dung Le","orcid":"https://orcid.org/0000-0003-4288-4249"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["ByteDance Inc.,SAMI","SAMI, ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,SAMI","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"SAMI, ByteDance Inc","institution_ids":["https://openalex.org/I43424612"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43424612"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1116","last_page":"1120"},"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":0.9987999796867371,"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":0.9896000027656555,"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":0.7920006513595581},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.6024049520492554},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.590083658695221},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5804175138473511},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5272539854049683},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5140917897224426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46401533484458923},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4506726861000061},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.42270034551620483},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4186323881149292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38067102432250977},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0855134129524231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920006513595581},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.6024049520492554},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.590083658695221},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5804175138473511},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5272539854049683},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5140917897224426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46401533484458923},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4506726861000061},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.42270034551620483},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4186323881149292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38067102432250977},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0855134129524231},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446088","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2039209917","https://openalex.org/W2519091744","https://openalex.org/W2898827701","https://openalex.org/W2972478942","https://openalex.org/W2998490864","https://openalex.org/W4224918587","https://openalex.org/W4224944643","https://openalex.org/W4282913091","https://openalex.org/W4287802874","https://openalex.org/W4288099666","https://openalex.org/W4307323391","https://openalex.org/W4318351475","https://openalex.org/W4318719023","https://openalex.org/W4319452539","https://openalex.org/W4319989813","https://openalex.org/W4322718191","https://openalex.org/W4372260308","https://openalex.org/W4372266552","https://openalex.org/W4377010126","https://openalex.org/W4380136719","https://openalex.org/W4380551955","https://openalex.org/W4383993968","https://openalex.org/W4388341054","https://openalex.org/W6610895800","https://openalex.org/W6776218486","https://openalex.org/W6803003856","https://openalex.org/W6838439425","https://openalex.org/W6839133533","https://openalex.org/W6840815571","https://openalex.org/W6848578254","https://openalex.org/W6848854281","https://openalex.org/W6849105126","https://openalex.org/W6849517043","https://openalex.org/W6849635556","https://openalex.org/W6850625674","https://openalex.org/W6853096648","https://openalex.org/W6853188576","https://openalex.org/W6853515095","https://openalex.org/W6854494257"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W1520183331","https://openalex.org/W2734842993","https://openalex.org/W2168175994","https://openalex.org/W2049473509"],"abstract_inverted_index":{"End-to-end":[0],"generation":[1,42],"of":[2,13,71,116],"musical":[3,50,125],"audio":[4,114],"using":[5,61,95],"deep":[6],"learning":[7],"techniques":[8],"has":[9],"seen":[10],"an":[11,36,84],"explosion":[12],"activity":[14],"recently.":[15],"However,":[16],"most":[17],"models":[18,43,94],"concentrate":[19],"on":[20,82,104],"generating":[21],"fully":[22],"mixed":[23],"music":[24,41,105],"in":[25],"response":[26],"to":[27,49],"abstract":[28],"conditioning":[29],"information.":[30],"In":[31],"this":[32],"work,":[33],"we":[34],"present":[35,68],"alternative":[37],"paradigm":[38],"for":[39],"producing":[40],"that":[44],"can":[45,58],"listen":[46],"and":[47,67,74,86,99],"respond":[48],"context.":[51,129],"We":[52,77,90],"describe":[53],"how":[54],"such":[55],"a":[56,62,69,87,100],"model":[57,65,111],"be":[59],"constructed":[60],"non-autoregressive,":[63],"transformer-based":[64],"architecture":[66,81],"number":[70],"novel":[72],"architectural":[73],"sampling":[75],"improvements.":[76],"train":[78],"the":[79,92,113],"described":[80],"both":[83],"open-source":[85],"proprietary":[88],"dataset.":[89],"evaluate":[91],"produced":[93],"standard":[96],"quality":[97,115],"metrics":[98],"new":[101],"approach":[102],"based":[103],"information":[106],"retrieval":[107],"descriptors.":[108],"The":[109],"resulting":[110],"reaches":[112],"state-of-the-art":[117],"text-conditioned":[118],"models,":[119],"as":[120,122],"well":[121],"exhibiting":[123],"strong":[124],"coherence":[126],"with":[127],"its":[128]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
