{"id":"https://openalex.org/W4416250726","doi":"https://doi.org/10.1109/waspaa66052.2025.11230941","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","display_name":"Fast Text-to-Audio Generation with Adversarial Post-Training","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250726","doi":"https://doi.org/10.1109/waspaa66052.2025.11230941"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","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/A5058107937","display_name":"Zachary Novack","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Novack","raw_affiliation_strings":["UC – San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC – San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014306278","display_name":"Zach Evans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zach Evans","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095767092","display_name":"Zack Zukowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zack Zukowski","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113116667","display_name":"Josiah Taylor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Josiah Taylor","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112345452","display_name":"CJ Carr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"CJ Carr","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034175373","display_name":"Julian D. Parker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Parker","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120499584","display_name":"Adnan Al-Sinan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156213","display_name":"American Rock Mechanics Association","ror":"https://ror.org/05vfrxy92","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156213"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adnan Al-Sinan","raw_affiliation_strings":["Arm"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arm","institution_ids":["https://openalex.org/I4210156213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gian Marco Iodice","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156213","display_name":"American Rock Mechanics Association","ror":"https://ror.org/05vfrxy92","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156213"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gian Marco Iodice","raw_affiliation_strings":["Arm"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arm","institution_ids":["https://openalex.org/I4210156213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["UC – San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC – San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["UC – San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC – San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8048,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91909289,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.34060001373291016,"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":0.34060001373291016,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.31299999356269836,"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":0.03790000081062317,"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/adversarial-system","display_name":"Adversarial system","score":0.9480000138282776},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6966999769210815},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4404999911785126},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9480000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756600022315979},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6966999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":18,"referenced_works":["https://openalex.org/W2763110165","https://openalex.org/W2791686384","https://openalex.org/W2939574508","https://openalex.org/W2962834855","https://openalex.org/W3099096615","https://openalex.org/W3205475937","https://openalex.org/W4225261970","https://openalex.org/W4250482878","https://openalex.org/W4372260310","https://openalex.org/W4372269936","https://openalex.org/W4402111476","https://openalex.org/W4402726956","https://openalex.org/W4402753769","https://openalex.org/W4403757510","https://openalex.org/W4403923215","https://openalex.org/W4404965447","https://openalex.org/W4408345930","https://openalex.org/W4415796735"],"related_works":[],"abstract_inverted_index":{"Text-to-audio":[0],"systems,":[1],"while":[2],"increasingly":[3],"performant,":[4],"are":[5],"slow":[6],"at":[7],"inference":[8],"time,":[9],"thus":[10],"making":[11],"their":[12,47],"latency":[13],"unpractical":[14],"for":[15,30],"many":[16],"creative":[17],"applications.":[18],"We":[19,83],"present":[20],"Adversarial":[21],"Relativistic-Contrastive":[22],"(ARC)":[23],"post-training,":[24],"the":[25,118],"first":[26],"adversarial":[27,39,63],"acceleration":[28],"algorithm":[29],"diffusion/flow":[31,66],"models":[32],"not":[33],"based":[34],"on":[35,109,114],"distillation.":[36],"While":[37],"past":[38],"post-training":[40,52,67,86],"methods":[41],"have":[42],"struggled":[43],"to":[44,65,78,91,122],"compare":[45],"against":[46],"expensive":[48],"distillation":[49],"counterparts,":[50],"ARC":[51,85],"is":[53],"a":[54,60,73,88,97,115],"simple":[55],"procedure":[56],"that":[57],"(1)":[58],"extends":[59],"recent":[61],"relativistic":[62],"formulation":[64],"and":[68,95,112],"(2)":[69],"combines":[70],"it":[71],"with":[72,87],"novel":[74],"contrastive":[75],"discriminator":[76],"objective":[77],"encourage":[79],"better":[80],"prompt":[81],"adherence.":[82],"pair":[84],"number":[89],"optimizations":[90],"Stable":[92],"Audio":[93],"Open":[94],"build":[96],"model":[98,121],"capable":[99],"of":[100,103],"generating":[101],"\u224812s":[102],"44.1kHz":[104],"stereo":[105],"audio":[106],"in":[107],"\u224875ms":[108],"an":[110],"H100,":[111],"\u22487s":[113],"mobile":[116],"edge-device,":[117],"fastest":[119],"text-to-audio":[120],"our":[123],"knowledge.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}