{"id":"https://openalex.org/W4392903114","doi":"https://doi.org/10.1109/icassp48485.2024.10447265","title":"MusicLDM: Enhancing Novelty in text-to-music Generation Using Beat-Synchronous mixup Strategies","display_name":"MusicLDM: Enhancing Novelty in text-to-music Generation Using Beat-Synchronous mixup Strategies","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903114","doi":"https://doi.org/10.1109/icassp48485.2024.10447265"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447265","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04766515/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California San Diego (UCSD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego (UCSD)","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102132394","display_name":"Yusong Wu","orcid":"https://orcid.org/0000-0003-4190-974X"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yusong Wu","raw_affiliation_strings":["Mila, Quebec Artificial Intelligence Institute, Universite de Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila, Quebec Artificial Intelligence Institute, Universite de Montreal","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["Centre for Vision Speech and Signal Processing, University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042252873","display_name":"Marianna Nezhurina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marianna Nezhurina","raw_affiliation_strings":["LAION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LAION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["University of California San Diego (UCSD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego (UCSD)","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego (UCSD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego (UCSD)","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1206","last_page":"1210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9969000220298767,"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/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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":0.7801371812820435},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.6671841144561768},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6295573115348816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5793206691741943},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47359398007392883},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39948809146881104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38185012340545654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3225255608558655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801371812820435},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.6671841144561768},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6295573115348816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5793206691741943},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47359398007392883},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39948809146881104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38185012340545654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3225255608558655},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447265","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"},{"id":"pmh:oai:HAL:hal-04766515v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766515","pdf_url":"https://hal.science/hal-04766515/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, France. pp.1206-1210, ⟨10.1109/ICASSP48485.2024.10447265⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04766515v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766515","pdf_url":"https://hal.science/hal-04766515/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, France. pp.1206-1210, ⟨10.1109/ICASSP48485.2024.10447265⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392903114.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2546879872","https://openalex.org/W2965373594","https://openalex.org/W2982753834","https://openalex.org/W3094550259","https://openalex.org/W4224035735","https://openalex.org/W4226442948","https://openalex.org/W4312933868","https://openalex.org/W4318351475","https://openalex.org/W4318718996","https://openalex.org/W4318719586","https://openalex.org/W4319989813","https://openalex.org/W4372260310","https://openalex.org/W4380136719","https://openalex.org/W4386076098","https://openalex.org/W6640963894","https://openalex.org/W6745136726","https://openalex.org/W6766673545","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6809885388","https://openalex.org/W6844204944","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6849141701","https://openalex.org/W6849416043","https://openalex.org/W6849517043","https://openalex.org/W6849635556","https://openalex.org/W6853096648"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W3011883280","https://openalex.org/W2369082698","https://openalex.org/W2401808953"],"abstract_inverted_index":{"Diffusion":[0,60],"models":[1],"have":[2],"shown":[3],"promising":[4],"results":[5],"in":[6],"cross-modal":[7],"generation":[8],"tasks,":[9],"including":[10],"text-to-image":[11],"and":[12,34,40,61,76,86,98,126,174,182,195],"text-to-audio":[13],"generation.":[14],"However,":[15],"generating":[16],"music,":[17,186],"as":[18,187,189],"a":[19,52,82,109],"special":[20],"type":[21],"of":[22,31,73,134,184],"audio,":[23],"presents":[24],"unique":[25],"challenges":[26],"due":[27],"to":[28,38,45,64,69,77,120,148,154,168],"limited":[29],"availability":[30],"music":[32,66,129,141],"data":[33,75,93],"sensitive":[35],"issues":[36],"related":[37],"copyright":[39],"plagiarism.":[41],"In":[42,152],"this":[43],"paper,":[44],"tackle":[46],"these":[47],"challenges,":[48],"we":[49,80,158],"first":[50],"construct":[51],"state-of-the-art":[53],"text-to-music":[54],"model,":[55],"MusicLDM,":[56],"that":[57,170],"adapts":[58],"Stable":[59],"AudioLDM":[62],"architectures":[63],"the":[65,71,118,131,135,139,149,180,190],"domain.":[67],"Then,":[68],"address":[70],"limitations":[72],"training":[74,104,124,136],"avoid":[78],"plagiarism,":[79],"leverage":[81],"beat":[83],"tracking":[84],"model":[85,119],"propose":[87],"two":[88],"different":[89],"mixup":[90,97,115,176],"strategies":[91,116,177],"for":[92],"augmentation:":[94],"beat-synchronous":[95,99,175],"audio":[96,105],"latent":[100,110],"mixup,":[101],"which":[102],"recombine":[103],"directly":[106],"or":[107],"via":[108],"embeddings":[111],"space,":[112],"respectively.":[113],"Such":[114],"encourage":[117],"interpolate":[121],"between":[122,192],"musical":[123],"samples":[125],"generate":[127],"new":[128,161],"within":[130],"convex":[132],"hull":[133],"data,":[137],"making":[138],"generated":[140,185,196],"more":[142],"diverse":[143],"while":[144],"still":[145],"staying":[146],"faithful":[147],"corresponding":[150],"style.":[151],"addition":[153],"popular":[155],"evaluation":[156,162],"metrics,":[157],"design":[159],"several":[160],"metrics":[163],"based":[164],"on":[165],"CLAP":[166],"score":[167],"demonstrate":[169],"our":[171],"proposed":[172],"MusicLDM":[173],"improve":[178],"both":[179],"quality":[181],"novelty":[183],"well":[188],"correspondence":[191],"input":[193],"text":[194],"music.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":13}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}