{"id":"https://openalex.org/W4408345930","doi":"https://doi.org/10.1109/icassp49660.2025.10888461","title":"Stable Audio Open","display_name":"Stable Audio Open","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345930","doi":"https://doi.org/10.1109/icassp49660.2025.10888461"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5014306278","display_name":"Zach Evans","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"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/A5034175373","display_name":"Julian D. Parker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian D. 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/A5107219635","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/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":"last","author":{"id":"https://openalex.org/A5104282899","display_name":"Jordi Pons","orcid":null},"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":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014306278"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":56.904,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.99934182,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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":0.9419000148773193,"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":0.9419000148773193,"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":0.9164000153541565,"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":0.6093968152999878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6093968152999878}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":30,"referenced_works":["https://openalex.org/W2939574508","https://openalex.org/W2972478942","https://openalex.org/W3094550259","https://openalex.org/W3205475937","https://openalex.org/W4307323391","https://openalex.org/W4372260310","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4396877837","https://openalex.org/W4411528087","https://openalex.org/W6703652217","https://openalex.org/W6734260513","https://openalex.org/W6769627184","https://openalex.org/W6776218486","https://openalex.org/W6779577414","https://openalex.org/W6779823529","https://openalex.org/W6809884996","https://openalex.org/W6838322825","https://openalex.org/W6845479124","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6849141701","https://openalex.org/W6849416043","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6858340110","https://openalex.org/W6858779713","https://openalex.org/W6861353174","https://openalex.org/W6862995742","https://openalex.org/W6864798992"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Open":[0],"generative":[1],"models":[2,24],"are":[3,25],"vitally":[4],"important":[5],"for":[6,10,30,87],"the":[7,40,60,66,72,79,82],"community,":[8],"allowing":[9],"fine-tunes":[11],"and":[12,27,32,42],"serving":[13],"as":[14],"baselines":[15],"when":[16],"presenting":[17],"new":[18,47],"models.":[19],"However,":[20],"most":[21],"current":[22],"text-to-audio":[23,49],"private":[26],"not":[28],"accessible":[29],"artists":[31],"researchers":[33],"to":[34],"build":[35],"upon.":[36],"Here":[37],"we":[38],"describe":[39],"architecture":[41],"training":[43],"process":[44],"of":[45,81],"a":[46],"open-weights":[48],"model":[50],"trained":[51],"with":[52,65],"Creative":[53],"Commons":[54],"data.":[55],"Our":[56],"evaluation":[57],"shows":[58],"that":[59],"model\u2019s":[61],"performance":[62],"is":[63],"competitive":[64],"state-of-the-art":[67],"across":[68],"various":[69],"metrics.":[70],"Notably,":[71],"reported":[73],"FD<inf":[74],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[75],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">openl3</inf>":[76],"results":[77],"(measuring":[78],"realism":[80],"generations)":[83],"showcase":[84],"its":[85],"potential":[86],"high-quality":[88],"stereo":[89],"sound":[90],"synthesis":[91],"at":[92],"44.1kHz.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":32}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-03-12T00:00:00"}