{"id":"https://openalex.org/W6892341465","doi":"https://doi.org/10.5281/zenodo.10265239","title":"IteraTTA: An Interface for Exploring Both Text Prompts and Audio Priors in Generating Music With Text-to-Audio Models","display_name":"IteraTTA: An Interface for Exploring Both Text Prompts and Audio Priors in Generating Music With Text-to-Audio Models","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6892341465","doi":"https://doi.org/10.5281/zenodo.10265239"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265239","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hiromu Yakura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiromu Yakura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Masataka Goto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30719472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.45100000500679016,"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":0.45100000500679016,"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":0.04520000144839287,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.04490000009536743,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/prior-probability","display_name":"Prior probability","score":0.766700029373169},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.5874999761581421},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4876999855041504},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.38920000195503235},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.37929999828338623},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3301999866962433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.766700029373169},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.48179998993873596},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4049000144004822},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37070000171661377},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.2879999876022339},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.26589998602867126},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265239","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265239","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5210826992988586,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5622405347","display_name":"\u4efb\u610f\u30c4\u30fc\u30eb\u3067\u306e\u30c7\u30b6\u30a4\u30f3\u652f\u63f4\u306e\u305f\u3081\u306eGAN\u3092\u7528\u3044\u305f\u30b5\u30f3\u30d7\u30eb\u6a21\u5023\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af","funder_award_id":"22KJ0353","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"text-to-audio":[1,88,170],"generation":[2,90,110],"techniques":[3,175],"have":[4,21],"the":[5,43,51,64,67,87,99,109,137,153],"potential":[6],"to":[7,11,37,42,63,97,124,178],"allow":[8],"novice":[9],"users":[10,31,60,74,96,126,142],"freely":[12],"generate":[13,38],"music":[14,55,89],"audio.":[15,39],"Even":[16],"if":[17],"they":[18],"do":[19],"not":[20,77],"musical":[22],"knowledge,":[23],"such":[24],"as":[25],"about":[26],"chord":[27],"progressions":[28],"and":[29,105,131,151,160,172],"instruments,":[30],"can":[32,143,176],"try":[33],"various":[34],"text":[35,79,103,129],"prompts":[36,80,104,130],"However,":[40],"compared":[41],"image":[44],"domain,":[45],"gaining":[46],"a":[47],"clear":[48],"understanding":[49,150],"of":[50,53,66,101,115,155],"space":[52,154],"possible":[54,156],"audios":[56,69],"is":[57,121],"difficult":[58],"because":[59],"cannot":[61],"listen":[62],"variations":[65],"generated":[68,138],"simultaneously.":[70],"We":[71],"therefore":[72],"facilitate":[73],"in":[75,127],"exploring":[76,152],"only":[78],"but":[81],"also":[82],"audio":[83,106,134],"priors":[84,107,135],"that":[85,165],"constrain":[86],"process.":[91],"This":[92],"dual-sided":[93],"exploration":[94],"enables":[95],"discern":[98],"impact":[100],"different":[102],"on":[108],"results":[111],"through":[112],"iterative":[113],"comparison":[114],"them.":[116],"Our":[117,158],"developed":[118],"interface,":[119],"IteraTTA,":[120],"specifically":[122,167],"designed":[123],"aid":[125],"refining":[128],"selecting":[132],"favorable":[133],"from":[136],"audios.":[139],"With":[140],"this,":[141],"progressively":[144],"reach":[145],"their":[146,179],"loosely-specified":[147],"goals":[148],"while":[149],"results.":[157],"implementation":[159],"discussions":[161],"highlight":[162],"design":[163],"considerations":[164],"are":[166],"required":[168],"for":[169],"models":[171],"how":[173],"interaction":[174],"contribute":[177],"effectiveness.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
