{"id":"https://openalex.org/W3174290991","doi":"https://doi.org/10.23919/dafx51585.2021.9768298","title":"A Generative Model for Raw Audio Using Transformer Architectures","display_name":"A Generative Model for Raw Audio Using Transformer Architectures","publication_year":2021,"publication_date":"2021-09-08","ids":{"openalex":"https://openalex.org/W3174290991","doi":"https://doi.org/10.23919/dafx51585.2021.9768298","mag":"3174290991"},"language":"en","primary_location":{"id":"doi:10.23919/dafx51585.2021.9768298","is_oa":false,"landing_page_url":"https://doi.org/10.23919/dafx51585.2021.9768298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th International Conference on Digital Audio Effects (DAFx)","raw_type":"proceedings-article"},"type":"preprint","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/A5017296738","display_name":"Prateek Verma","orcid":"https://orcid.org/0000-0002-6402-8948"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prateek Verma","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics Stanford University,Stanford,CA,USA","Center for Computer Research in Music and Acoustics Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088100932","display_name":"Chris Chafe","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Chafe","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics Stanford University,Stanford,CA,USA","Center for Computer Research in Music and Acoustics Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017296738"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.7759,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91095799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9991000294685364,"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":0.7908475399017334},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7475628852844238},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5995554327964783},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5785098075866699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344217419624329},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5124140381813049},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49328893423080444},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48424479365348816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4441414177417755},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44003236293792725},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35612010955810547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34897834062576294},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1020841896533966},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09010681509971619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908475399017334},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7475628852844238},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5995554327964783},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5785098075866699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344217419624329},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5124140381813049},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49328893423080444},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48424479365348816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4441414177417755},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44003236293792725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35612010955810547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34897834062576294},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1020841896533966},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09010681509971619},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/dafx51585.2021.9768298","is_oa":false,"landing_page_url":"https://doi.org/10.23919/dafx51585.2021.9768298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th International Conference on Digital Audio Effects (DAFx)","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":98,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1566660863","https://openalex.org/W2072752513","https://openalex.org/W2108598243","https://openalex.org/W2120847449","https://openalex.org/W2134900903","https://openalex.org/W2191779130","https://openalex.org/W2296724634","https://openalex.org/W2398826216","https://openalex.org/W2402144811","https://openalex.org/W2516301810","https://openalex.org/W2519091744","https://openalex.org/W2540404261","https://openalex.org/W2560180317","https://openalex.org/W2593116425","https://openalex.org/W2626778328","https://openalex.org/W2749651610","https://openalex.org/W2752796333","https://openalex.org/W2777302760","https://openalex.org/W2782490852","https://openalex.org/W2795935131","https://openalex.org/W2803963372","https://openalex.org/W2811079561","https://openalex.org/W2896457183","https://openalex.org/W2901997113","https://openalex.org/W2916113431","https://openalex.org/W2936975153","https://openalex.org/W2940744433","https://openalex.org/W2941115821","https://openalex.org/W2949382160","https://openalex.org/W2950547518","https://openalex.org/W2953384591","https://openalex.org/W2963011080","https://openalex.org/W2963103134","https://openalex.org/W2963212250","https://openalex.org/W2963233633","https://openalex.org/W2963341956","https://openalex.org/W2963452667","https://openalex.org/W2963563276","https://openalex.org/W2963609956","https://openalex.org/W2963782041","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2973049837","https://openalex.org/W2979476256","https://openalex.org/W2981851019","https://openalex.org/W2996383576","https://openalex.org/W3003257820","https://openalex.org/W3010387158","https://openalex.org/W3021164770","https://openalex.org/W3030163527","https://openalex.org/W3036601975","https://openalex.org/W3042610466","https://openalex.org/W3090140450","https://openalex.org/W3093494400","https://openalex.org/W3094502228","https://openalex.org/W3099782249","https://openalex.org/W3103145119","https://openalex.org/W3119866685","https://openalex.org/W3158129762","https://openalex.org/W4287391717","https://openalex.org/W4287802874","https://openalex.org/W4288374038","https://openalex.org/W4292779060","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4301107988","https://openalex.org/W4301368689","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6697040288","https://openalex.org/W6713134421","https://openalex.org/W6729053843","https://openalex.org/W6739901393","https://openalex.org/W6747635987","https://openalex.org/W6748409065","https://openalex.org/W6750732768","https://openalex.org/W6751512325","https://openalex.org/W6752096078","https://openalex.org/W6753018729","https://openalex.org/W6755182157","https://openalex.org/W6755207826","https://openalex.org/W6755406732","https://openalex.org/W6761447021","https://openalex.org/W6761628794","https://openalex.org/W6763509872","https://openalex.org/W6768028577","https://openalex.org/W6769196770","https://openalex.org/W6774110404","https://openalex.org/W6776218486","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6780311315","https://openalex.org/W6784559596","https://openalex.org/W6794463088","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495"],"abstract_inverted_index":{"This":[0,30],"paper":[1],"proposes":[2],"a":[3,19,51,61,121,137],"novel":[4,144],"way":[5],"of":[6,87,126,140,146],"doing":[7],"audio":[8,80,132,153],"synthesis":[9,154],"at":[10],"the":[11,44,66,70,75,85,88,127,174],"waveform":[12,103],"level":[13],"using":[14,147,169],"Transformer":[15],"architectures.":[16],"We":[17,91,105],"propose":[18],"deep":[20],"neural":[21],"network":[22],"for":[23,64,84,101,151],"generating":[24,161],"waveforms,":[25],"similar":[26,62,165],"to":[27,58,77,130,166,172],"wavenet":[28,54],"[1].":[29],"is":[31],"fully":[32],"probabilistic,":[33],"auto-regressive,":[34],"and":[35],"causal,":[36],"i.e.":[37],"each":[38],"sample":[39],"generated":[40],"depends":[41],"on":[42,60],"only":[43],"previously":[45],"observed":[46],"samples.":[47],"Our":[48],"approach":[49,145],"outperforms":[50],"widely":[52],"used":[53,100],"architecture":[55,76],"by":[56,114,117],"up":[57],"9%":[59],"dataset":[63],"predicting":[65],"next":[67],"step.":[68],"Using":[69],"attention":[71],"mechanism,":[72],"we":[73],"enable":[74],"learn":[78],"which":[79],"samples":[81,119],"are":[82],"important":[83],"prediction":[86],"future":[89],"sample.":[90],"show":[92,107],"how":[93],"causal":[94],"transformer":[95,149],"generative":[96,148],"models":[97],"can":[98,111],"be":[99,112],"raw":[102,152],"synthesis.":[104],"also":[106],"that":[108],"this":[109],"performance":[110],"improved":[113],"another":[115],"2%":[116],"conditioning":[118],"over":[120],"wider":[122],"context.":[123],"The":[124,143],"flexibility":[125],"current":[128],"model":[129],"synthesize":[131],"from":[133,160],"latent":[134,170],"representations":[135],"suggests":[136],"large":[138],"number":[139],"potential":[141],"applications.":[142],"architectures":[150],"is,":[155],"however,":[156],"still":[157],"far":[158],"away":[159],"any":[162],"meaningful":[163],"music":[164],"wavenet,":[167],"without":[168],"codes/meta-data":[171],"aid":[173],"generation":[175],"process.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}