{"id":"https://openalex.org/W6968316755","doi":"https://doi.org/10.5281/zenodo.14877327","title":"Diff-a-Riff: Musical Accompaniment Co-Creation via Latent Diffusion Models","display_name":"Diff-a-Riff: Musical Accompaniment Co-Creation via Latent Diffusion Models","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968316755","doi":"https://doi.org/10.5281/zenodo.14877327"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877327","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877327","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.14877327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Javier Nistal","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Javier Nistal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Marco Pasini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Pasini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cyran Aouameur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cyran Aouameur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Maarten Grachten","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarten Grachten","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Stefan Lattner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.4131515,"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":0.6556000113487244,"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":0.6556000113487244,"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":0.25780001282691956,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0142000000923872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.630299985408783},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.6162999868392944},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.546999990940094},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.524399995803833},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5181999802589417},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5170999765396118},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769000291824341},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.630299985408783},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.546999990940094},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3968999981880188},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.2964000105857849},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2581000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877327","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877327","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.14877327","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877327","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":0.5349990725517273,"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":{"Recent":[0],"advancements":[1],"in":[2,48],"deep":[3],"generative":[4],"models":[5],"present":[6],"new":[7],"opportunities":[8],"for":[9],"music":[10,49],"production":[11],"but":[12],"also":[13],"pose":[14],"challenges,":[15],"such":[16],"as":[17],"high":[18],"computational":[19],"demands":[20],"and":[21,34,85,95,106],"limited":[22],"audio":[23,79,89],"quality.":[24],"Moreover,":[25],"current":[26],"systems":[27],"frequently":[28],"rely":[29],"solely":[30],"on":[31,37,114],"text":[32,81],"input":[33],"typically":[35],"focus":[36],"producing":[38],"complete":[39],"musical":[40,71],"pieces,":[41],"which":[42],"is":[43],"incompatible":[44],"with":[45,110],"existing":[46],"workflows":[47],"production.":[50],"To":[51],"address":[52],"these":[53],"issues,":[54],"we":[55],"introduce":[56],"Diff-A-Riff,":[57],"a":[58],"Latent":[59],"Diffusion":[60],"Model":[61],"designed":[62],"to":[63,69],"generate":[64],"high-quality":[65],"instrumental":[66],"accompaniments":[67],"adaptable":[68],"any":[70],"context.":[72],"This":[73],"model":[74],"offers":[75],"control":[76],"through":[77,103],"either":[78],"references,":[80],"prompts,":[82],"or":[83],"both,":[84],"produces":[86],"48kHz":[87],"pseudo-stereo":[88],"while":[90],"significantly":[91],"reducing":[92],"inference":[93],"time":[94],"memory":[96],"usage.":[97],"We":[98],"demonstrate":[99],"the":[100,115],"model's":[101],"capabilities":[102],"objective":[104],"metrics":[105],"subjective":[107],"listening":[108],"tests,":[109],"extensive":[111],"examples":[112],"available":[113],"accompanying":[116],"website.":[117]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}