{"id":"https://openalex.org/W7148548915","doi":"https://doi.org/10.1109/asru65441.2025.11434607","title":"Advancing Controllable Music Generation with Latent Rectified Flow Guided by Rhythm and Harmony","display_name":"Advancing Controllable Music Generation with Latent Rectified Flow Guided by Rhythm and Harmony","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148548915","doi":"https://doi.org/10.1109/asru65441.2025.11434607"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5027896769","display_name":"Haibin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haibin Yu","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121285708","display_name":"Jiayi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayi Zhou","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391700","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-6853-7785"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132815682","display_name":"Zhiming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiming Wang","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132802233","display_name":"Huijia Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129685555","display_name":"Yanmin Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027896769"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75036817,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9623000025749207,"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":0.9623000025749207,"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":0.008899999782443047,"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/T12290","display_name":"Human Motion and Animation","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.730400025844574},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (color)","score":0.5795999765396118},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.3181999921798706}],"concepts":[{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.730400025844574},{"id":"https://openalex.org/C2776453491","wikidata":"https://www.wikidata.org/wiki/Q5659234","display_name":"Harmony (color)","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5296000242233276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43130001425743103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2662999927997589},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2760103357","https://openalex.org/W2972478942","https://openalex.org/W4233034753","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4390873054","https://openalex.org/W4392902957","https://openalex.org/W4392903114","https://openalex.org/W4392904491","https://openalex.org/W4392931781","https://openalex.org/W4396877837","https://openalex.org/W4401043564","https://openalex.org/W4402112302","https://openalex.org/W4404835690","https://openalex.org/W4408353232"],"related_works":[],"abstract_inverted_index":{"Rectified":[0],"flow":[1,82,106],"models":[2,21],"have":[3],"shown":[4],"considerable":[5],"potential":[6],"in":[7],"various":[8],"generation":[9,16,46,60,71],"tasks,":[10],"but":[11],"their":[12],"capability":[13],"for":[14],"music":[15,86],"remains":[17],"largely":[18],"unexplored.":[19],"These":[20],"use":[22],"ordinary":[23],"differential":[24],"equations":[25],"(ODEs)":[26],"with":[27],"linear":[28],"interpolation,":[29],"allowing":[30],"more":[31],"straightforward":[32],"distribution":[33],"transportation":[34],"compared":[35],"to":[36,54,108],"diffusion":[37,95],"models.":[38,98],"In":[39],"this":[40],"paper,":[41],"we":[42,62],"present":[43],"a":[44],"text-to-music":[45],"framework":[47],"based":[48,93],"on":[49,94,115],"latent":[50],"rectified":[51,81,105],"flow.":[52],"Additionally,":[53],"further":[55],"improve":[56],"its":[57],"controllability":[58],"and":[59,65,75,96],"quality,":[61],"inject":[63],"rhythmic":[64],"harmonic":[66],"control":[67],"signals":[68],"into":[69],"the":[70,80,104],"process.":[72],"Extensive":[73],"objective":[74],"subjective":[76],"evaluations":[77],"demonstrate":[78],"that":[79],"model":[83,107],"can":[84],"generate":[85],"of":[87],"comparable":[88],"quality":[89],"as":[90],"existing":[91],"systems":[92],"language":[97],"Furthermore,":[99],"integrating":[100],"external":[101],"controls":[102],"enables":[103],"achieve":[109],"improved":[110],"performance.":[111],"Samples":[112],"are":[113],"available":[114],"https://anonymous.4open.science/w/MusicLRF-demo-2DA3/":[116]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}