{"id":"https://openalex.org/W4408353321","doi":"https://doi.org/10.1109/icassp49660.2025.10887608","title":"Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance","display_name":"Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353321","doi":"https://doi.org/10.1109/icassp49660.2025.10887608"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887608","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/A5020574555","display_name":"Xuchan Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","US"],"is_corresponding":true,"raw_author_name":"Xuchan Bao","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071459336","display_name":"Judith Yue Li","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Judith Yue Li","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027095108","display_name":"Zhong Wan","orcid":"https://orcid.org/0000-0003-3652-2460"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Zhong Yi Wan","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057986343","display_name":"Kun Su","orcid":"https://orcid.org/0000-0002-7793-1853"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Kun Su","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038217434","display_name":"Timo I. Denk","orcid":"https://orcid.org/0009-0007-3727-6149"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Timo Denk","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859889","display_name":"Joonseok Lee","orcid":"https://orcid.org/0000-0002-0786-8086"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Joonseok Lee","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068428403","display_name":"Dima Kuzmin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Dima Kuzmin","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008648105","display_name":"Fei Sha","orcid":"https://orcid.org/0009-0006-1733-5482"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Fei Sha","raw_affiliation_strings":["University of Toronto, Google"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Google","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5020574555"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0539878,"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":0.9998999834060669,"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":0.9886999726295471,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410731315612793},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6650985479354858},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5082008838653564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4909816086292267},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4349513351917267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4116849899291992},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37351536750793457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410731315612793},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6650985479354858},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5082008838653564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909816086292267},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4349513351917267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4116849899291992},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37351536750793457},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887608","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2512971201","https://openalex.org/W3012950066","https://openalex.org/W4312933868","https://openalex.org/W4372266552","https://openalex.org/W4396877837","https://openalex.org/W4402727350","https://openalex.org/W6631190155","https://openalex.org/W6664257448","https://openalex.org/W6726497184","https://openalex.org/W6728047685","https://openalex.org/W6765779288","https://openalex.org/W6791353385","https://openalex.org/W6814835349","https://openalex.org/W6838452192","https://openalex.org/W6840815571","https://openalex.org/W6841982715","https://openalex.org/W6849105126"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Modern":[0],"music":[1,49,102],"retrieval":[2,21,33,118,123],"systems":[3],"often":[4],"rely":[5],"on":[6,70],"fixed":[7],"representations":[8],"of":[9,84,122],"user":[10,56,85,132],"preferences,":[11,133],"limiting":[12],"their":[13],"ability":[14],"to":[15,40,58,135],"capture":[16],"users\u2019":[17],"diverse":[18,42,137],"and":[19,81,100,115,124,138],"uncertain":[20],"needs.":[22],"To":[23],"address":[24],"this":[25],"limitation,":[26],"we":[27],"introduce":[28],"Diff4Steer,":[29],"a":[30,59,67],"novel":[31],"generative":[32,117],"framework":[34,110],"that":[35,54],"employs":[36],"lightweight":[37],"diffusion":[38],"models":[39],"synthesize":[41],"seed":[43],"embeddings":[44],"representing":[45],"potential":[46],"directions":[47],"for":[48,75],"exploration.":[50],"Unlike":[51],"deterministic":[52,112],"methods":[53,114],"map":[55],"query":[57],"single":[60],"point":[61],"in":[62,120,130],"embedding":[63],"space,":[64],"Diff4Steer":[65,88],"provides":[66],"statistical":[68],"prior":[69],"the":[71,79],"target":[72],"modality":[73],"(audio)":[74],"retrieval,":[76],"effectively":[77],"capturing":[78,131],"uncertainty":[80],"multi-faceted":[82],"nature":[83],"preferences.":[86],"Furthermore,":[87],"can":[89],"be":[90],"steered":[91],"by":[92],"image":[93],"or":[94],"text":[95],"inputs,":[96],"enabling":[97],"more":[98,136],"flexible":[99],"controllable":[101],"discovery":[103],"combined":[104],"with":[105],"nearest":[106],"neighbor":[107],"search.":[108],"Our":[109],"outperforms":[111],"regression":[113],"LLM-based":[116],"baseline":[119],"terms":[121],"ranking":[125],"metrics,":[126],"demonstrating":[127],"its":[128],"effectiveness":[129],"leading":[134],"relevant":[139],"recommendations.":[140],"Listening":[141],"examples":[142],"are":[143],"available":[144],"at":[145],"tinyurl.com/diff4steer.":[146]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}