{"id":"https://openalex.org/W4408355840","doi":"https://doi.org/10.1109/icassp49660.2025.10889289","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","display_name":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355840","doi":"https://doi.org/10.1109/icassp49660.2025.10889289"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5008123626","display_name":"Jisi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jisi Zhang","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060097629","display_name":"Pablo Peso Parada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pablo Peso Parada","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113981675","display_name":"Md Asif Jalal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Md Asif Jalal","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104088631","display_name":"Karthikeyan Saravanan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karthikeyan Saravanan","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008123626"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05803984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9930999875068665,"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":0.9930999875068665,"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":0.9598000049591064,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9527000188827515,"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/diffusion","display_name":"Diffusion","score":0.6435826420783997},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.597265899181366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3639605641365051},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1562943160533905}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6435826420783997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597265899181366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3639605641365051},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1562943160533905},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2760103357","https://openalex.org/W2972478942","https://openalex.org/W3094550259","https://openalex.org/W3096918678","https://openalex.org/W3105816068","https://openalex.org/W3156636935","https://openalex.org/W3194782062","https://openalex.org/W4312933868","https://openalex.org/W4372260250","https://openalex.org/W4372260310","https://openalex.org/W4372260340","https://openalex.org/W4392903114","https://openalex.org/W4396877837","https://openalex.org/W4401043564","https://openalex.org/W4403674737","https://openalex.org/W4404037229","https://openalex.org/W4408345930","https://openalex.org/W6732646663","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6763945542","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6791353385","https://openalex.org/W6794146050","https://openalex.org/W6795261426","https://openalex.org/W6797906067","https://openalex.org/W6809884996","https://openalex.org/W6840815571","https://openalex.org/W6841982715","https://openalex.org/W6846655393","https://openalex.org/W6847076894","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6853096648","https://openalex.org/W6861353174"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Diffusion":[0],"based":[1,13,39],"Text-To-Music":[2],"(TTM)":[3],"models":[4,15],"generate":[5],"music":[6],"corresponding":[7],"to":[8,77,130,151,161],"text":[9,18,82,157,176,199,211],"descriptions.":[10],"Typically":[11],"UNet":[12,44],"diffusion":[14,38,73],"condition":[16],"on":[17,47,167,206],"embeddings":[19,150,155,171,177,183,212],"generated":[20],"from":[21,28,84,91,105,179],"a":[22,29,37,50,60,80,88,132,162],"pre-trained":[23],"large":[24],"language":[25,52],"model":[26,53,64,74,140,164,204],"or":[27],"cross-modality":[30],"audio-language":[31,62],"representation":[32,63,83,90],"model.":[33],"This":[34,119],"work":[35],"proposes":[36],"TTM,":[40],"in":[41,226],"which":[42],"the":[43,85,92,106,122,137,147,152,168,180,185,203,229],"is":[45,75,219],"conditioned":[46,205],"both":[48,79,100,207],"(i)":[49],"uni-modal":[51],"(e.g.,":[54,65,128],"T5)":[55],"via":[56,67],"cross-attention":[57],"and":[58,87,102,116,209,214],"(ii)":[59],"cross-modal":[61],"CLAP)":[66,129],"Feature-wise":[68],"Linear":[69],"Modulation":[70],"(FiLM).":[71],"The":[72],"trained":[76],"exploit":[78],"local":[81,103,154,170,182],"T5":[86,107,153,169,181,210],"global":[89,101,133,149,175],"CLAP.":[93],"Furthermore,":[94],"we":[95,112],"propose":[96],"modifications":[97],"that":[98,111,145],"extract":[99,131],"representations":[104],"through":[108,184],"pooling":[109,115,188],"mechanisms":[110],"call":[113],"mean":[114,187],"self-attention":[117],"pooling.":[118],"approach":[120,189],"mitigates":[121],"need":[123],"for":[124],"an":[125],"additional":[126],"encoder":[127],"representation,":[134],"thereby":[135],"reducing":[136],"number":[138,230],"of":[139,228,231],"parameters.":[141],"Our":[142,216],"results":[143],"show":[144],"incorporating":[146],"CLAP":[148,208],"enhances":[156],"adherence":[158,200],"(KL=1.47)":[159],"compared":[160],"baseline":[163],"solely":[165],"relying":[166],"(KL=1.54).":[172],"Alternatively,":[173],"extracting":[174],"directly":[178],"proposed":[186,217],"yields":[190],"superior":[191],"generation":[192],"quality":[193],"(FAD=1.89)":[194],"while":[195],"exhibiting":[196],"marginally":[197],"inferior":[198],"(KL=1.51)":[201],"against":[202],"(FAD=1.94":[213],"KL=1.47).":[215],"solution":[218],"not":[220],"only":[221],"efficient":[222],"but":[223],"also":[224],"compact":[225],"terms":[227],"parameters":[232],"required.":[233]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}