{"id":"https://openalex.org/W4392908898","doi":"https://doi.org/10.1109/icassp48485.2024.10446400","title":"Bass Accompaniment Generation Via Latent Diffusion","display_name":"Bass Accompaniment Generation Via Latent Diffusion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908898","doi":"https://doi.org/10.1109/icassp48485.2024.10446400"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5041479451","display_name":"Marco Pasini","orcid":"https://orcid.org/0000-0002-1430-7535"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210131385","display_name":"Sony (France)","ror":"https://ror.org/03cr99w51","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210131385","https://openalex.org/I4210143797"]}],"countries":["FR","GB"],"is_corresponding":true,"raw_author_name":"Marco Pasini","raw_affiliation_strings":["Sony Computer Science Laboratories,Paris,France","Sony Computer Science Laboratories, Paris, France","Queen Mary University, London, UK"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Paris,France","institution_ids":["https://openalex.org/I4210131385"]},{"raw_affiliation_string":"Sony Computer Science Laboratories, Paris, France","institution_ids":["https://openalex.org/I4210131385"]},{"raw_affiliation_string":"Queen Mary University, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050343712","display_name":"Maarten Grachten","orcid":"https://orcid.org/0000-0002-9488-0840"},"institutions":[{"id":"https://openalex.org/I4210131385","display_name":"Sony (France)","ror":"https://ror.org/03cr99w51","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210131385","https://openalex.org/I4210143797"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maarten Grachten","raw_affiliation_strings":["Sony Computer Science Laboratories,Paris,France","Sony Computer Science Laboratories, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Paris,France","institution_ids":["https://openalex.org/I4210131385"]},{"raw_affiliation_string":"Sony Computer Science Laboratories, Paris, France","institution_ids":["https://openalex.org/I4210131385"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053442723","display_name":"Stefan Lattner","orcid":"https://orcid.org/0000-0002-3945-7580"},"institutions":[{"id":"https://openalex.org/I4210131385","display_name":"Sony (France)","ror":"https://ror.org/03cr99w51","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210131385","https://openalex.org/I4210143797"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":["Sony Computer Science Laboratories,Paris,France","Sony Computer Science Laboratories, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Paris,France","institution_ids":["https://openalex.org/I4210131385"]},{"raw_affiliation_string":"Sony Computer Science Laboratories, Paris, France","institution_ids":["https://openalex.org/I4210131385"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041479451"],"corresponding_institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210131385"],"apc_list":null,"apc_paid":null,"fwci":2.7642,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90798749,"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":"1166","last_page":"1170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9789000153541565,"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/T10860","display_name":"Speech and Audio Processing","score":0.9789000153541565,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9785000085830688,"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/T11309","display_name":"Music and Audio Processing","score":0.9635999798774719,"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/bass","display_name":"Bass (fish)","score":0.7499297857284546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5738901495933533},{"id":"https://openalex.org/keywords/fishery","display_name":"Fishery","score":0.1409679353237152},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07508397102355957}],"concepts":[{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.7499297857284546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5738901495933533},{"id":"https://openalex.org/C505870484","wikidata":"https://www.wikidata.org/wiki/Q180538","display_name":"Fishery","level":1,"score":0.1409679353237152},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07508397102355957}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":43,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2519091744","https://openalex.org/W3088329082","https://openalex.org/W3094550259","https://openalex.org/W4221148975","https://openalex.org/W4281485151","https://openalex.org/W4287802874","https://openalex.org/W4288099666","https://openalex.org/W4309117899","https://openalex.org/W4312349930","https://openalex.org/W4312933868","https://openalex.org/W4318351475","https://openalex.org/W4319452539","https://openalex.org/W4380136719","https://openalex.org/W4385570645","https://openalex.org/W4389977645","https://openalex.org/W4394625831","https://openalex.org/W4401110409","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6679045638","https://openalex.org/W6730558285","https://openalex.org/W6732429163","https://openalex.org/W6739901393","https://openalex.org/W6755257315","https://openalex.org/W6757817989","https://openalex.org/W6758675244","https://openalex.org/W6760601182","https://openalex.org/W6763945542","https://openalex.org/W6771763809","https://openalex.org/W6776218486","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6795986329","https://openalex.org/W6803922201","https://openalex.org/W6809884996","https://openalex.org/W6838639034","https://openalex.org/W6840815571","https://openalex.org/W6841472891","https://openalex.org/W6853096648","https://openalex.org/W6855355973"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W587891163","https://openalex.org/W1991830762","https://openalex.org/W2782013024","https://openalex.org/W2011560150","https://openalex.org/W2076114088","https://openalex.org/W2494322668","https://openalex.org/W2134105472","https://openalex.org/W611295337"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,27,91,96,113,174],"automatically":[3],"generate":[4,153],"music":[5,178],"that":[6,43,59],"appropriately":[7],"matches":[8],"an":[9,122,146],"arbitrary":[10,32],"input":[11,62,147],"track":[12],"is":[13],"a":[14,19,54,67,75,89,97,131,165],"challenging":[15],"task.":[16],"We":[17,126],"present":[18],"novel":[20],"controllable":[21,159],"system":[22,151],"for":[23],"generating":[24,121],"single":[25],"stems":[26],"accompany":[28],"musical":[29],"mixes":[30,136],"of":[31,37,66,74,84,133,135],"length.":[33],"At":[34],"the":[35,63,71,82,93,149],"core":[36],"our":[38,128],"method":[39],"are":[40],"audio":[41,46,107,161],"autoencoders":[42],"efficiently":[44],"compress":[45],"waveform":[47],"samples":[48],"into":[49],"invertible":[50],"latent":[51,56,64,72,94,124],"representations,":[52],"and":[53,69,137],"conditional":[55,160],"diffusion":[57,102],"model":[58,129],"takes":[60],"as":[61],"encoding":[65,73],"mix":[68],"generates":[70],"corresponding":[76],"stem.":[77],"To":[78],"provide":[79],"control":[80],"over":[81],"timbre":[83],"generated":[85],"samples,":[86],"we":[87,109],"introduce":[88],"technique":[90],"ground":[92],"space":[95],"user-provided":[98],"reference":[99],"style":[100],"during":[101],"sampling.":[103],"For":[104],"further":[105],"improving":[106],"quality,":[108],"adapt":[110],"classifier-free":[111],"guidance":[112,118],"avoid":[114],"distortions":[115],"at":[116],"high":[117],"strengths":[119],"when":[120],"unbounded":[123],"space.":[125],"train":[127],"on":[130],"dataset":[132],"pairs":[134],"matching":[138],"bass":[139],"stems.":[140],"Quantitative":[141],"experiments":[142],"demonstrate":[143],"that,":[144],"given":[145],"mix,":[148],"proposed":[150],"can":[152],"basslines":[154],"with":[155],"user-specified":[156],"timbres.":[157],"Our":[158],"generation":[162],"framework":[163],"represents":[164],"significant":[166],"step":[167],"forward":[168],"in":[169,177],"creating":[170],"generative":[171],"AI":[172],"tools":[173],"assist":[175],"musicians":[176],"production.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}