{"id":"https://openalex.org/W7108666778","doi":"https://doi.org/10.5281/zenodo.17811364","title":"GD-Retriever: Controllable generative text-music retrieval with diffusion models","display_name":"GD-Retriever: Controllable generative text-music retrieval with diffusion models","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108666778","doi":"https://doi.org/10.5281/zenodo.17811364"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811364","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811364","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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Julien Guinot","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Julien Guinot","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Elio Quinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elio Quinton","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"George Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Fazekas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.62967989,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.652999997138977,"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":0.652999997138977,"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/T10028","display_name":"Topic Modeling","score":0.09179999679327011,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.03709999844431877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/embedding","display_name":"Embedding","score":0.5964999794960022},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5329999923706055},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.501800000667572},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4684999883174896},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4684000015258789},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4278999865055084},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.40070000290870667},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.320499986410141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261000275611877},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406000018119812},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4684000015258789},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811364","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811364","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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811364","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811364","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":""},"sustainable_development_goals":[{"score":0.6064847111701965,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"contrastive":[1,106],"models":[2,68,91,108],"have":[3],"achieved":[4],"strong":[5],"performance":[6,104],"in":[7,51,72,98,112],"text-audio":[8],"retrieval":[9,99,103,111,130,137],"and":[10,33,87,109],"zero-shot":[11],"settings,":[12],"but":[13],"improving":[14],"joint":[15],"embedding":[16],"spaces":[17,115],"remains":[18],"an":[19],"active":[20],"research":[21],"area.":[22],"Less":[23],"attention":[24],"has":[25],"been":[26],"given":[27],"to":[28,69],"making":[29],"these":[30],"systems":[31],"controllable":[32],"interactive":[34,133],"for":[35,135],"users.":[36],"In":[37],"text-music":[38,136],"retrieval,":[39],"the":[40],"ambiguity":[41],"of":[42,129],"freeform":[43],"language":[44],"creates":[45],"a":[46,62,73,95],"many-to-many":[47],"mapping,":[48],"often":[49],"resulting":[50],"inflexible":[52],"or":[53],"unsatisfying":[54],"results.":[55],"We":[56],"introduce":[57],"Generative":[58],"Diffusion":[59],"Retriever":[60],"(GDR),":[61],"novel":[63],"framework":[64],"that":[65,123],"leverages":[66],"diffusion":[67,89],"generate":[70],"queries":[71],"retrieval-optimized":[74],"latent":[75,114],"space.":[76],"This":[77],"enables":[78,125],"controllability":[79],"through":[80],"generative":[81],"tools":[82],"such":[83],"as":[84],"negative":[85],"prompting":[86],"denoising":[88],"implicit":[90],"(DDIM)":[92],"inversion,":[93],"opening":[94],"new":[96],"direction":[97],"control.":[100],"GDR":[101,124],"improves":[102],"over":[105],"teacher":[107],"supports":[110],"audio-only":[113],"using":[116],"non-jointly":[117],"trained":[118],"encoders.":[119],"Finally,":[120],"we":[121],"demonstrate":[122],"effective":[126],"post-hoc":[127],"manipulation":[128],"behavior,":[131],"enhancing":[132],"control":[134],"tasks.":[138]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}
