{"id":"https://openalex.org/W4415708003","doi":"https://doi.org/10.1109/icme59968.2025.11209133","title":"An Investigation on Audio-Prompt and Structure Guided Long-Duration Music Generation Based on Diffusion Models","display_name":"An Investigation on Audio-Prompt and Structure Guided Long-Duration Music Generation Based on Diffusion Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708003","doi":"https://doi.org/10.1109/icme59968.2025.11209133"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100574224","display_name":"Ziyu Zhao","orcid":"https://orcid.org/0000-0002-6578-0023"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Zhao","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089001438","display_name":"Zilu Guo","orcid":"https://orcid.org/0009-0000-0486-6088"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilu Guo","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412670","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2410-2429"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074945035","display_name":"Feng Ma","orcid":"https://orcid.org/0000-0002-1357-3006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Ma","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078579500","display_name":"Jia Hong Pan","orcid":"https://orcid.org/0000-0002-4812-4331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6730999946594238,"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":0.6730999946594238,"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":0.19030000269412994,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.024299999698996544,"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/remainder","display_name":"Remainder","score":0.6402000188827515},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5708000063896179},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.541100025177002},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.5382000207901001},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5349000096321106},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4632999897003174},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C39613435","wikidata":"https://www.wikidata.org/wiki/Q846677","display_name":"Remainder","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4632999897003174},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1559975096","https://openalex.org/W2296153915","https://openalex.org/W4312933868","https://openalex.org/W4387969125","https://openalex.org/W4390872297","https://openalex.org/W4390873332","https://openalex.org/W4392903114","https://openalex.org/W4396877837","https://openalex.org/W4401043564","https://openalex.org/W4408345930","https://openalex.org/W4414361356"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"text-to-music":[1],"generation":[2,53,118,163],"models":[3],"face":[4],"two":[5,47],"main":[6],"limitations:":[7],"they":[8,26],"either":[9],"only":[10],"generate":[11],"approximately":[12],"10":[13],"seconds":[14],"of":[15,19,72,96,108,119,122,134,167],"music,":[16],"falling":[17],"short":[18],"users\u2019":[20],"needs":[21],"for":[22,35,50],"longer":[23],"compositions,":[24],"or":[25],"require":[27],"longer-duration":[28],"datasets":[29],"and":[30,41],"increased":[31],"output":[32],"feature":[33],"dimensions":[34],"training,":[36],"leading":[37],"to":[38,82,103,115],"higher":[39],"data":[40],"computational":[42],"costs.":[43],"We":[44],"systematically":[45],"explored":[46],"training-free":[48],"strategies":[49],"long-duration":[51,169],"music":[52,162],"based":[54],"on":[55],"diffusion":[56],"models.":[57],"Both":[58],"methods":[59],"divide":[60],"the":[61,84,90,94,100,109,117,120,123,128,132,142,147,152],"task":[62],"into":[63],"multiple":[64],"stages,":[65],"where":[66],"each":[67,77],"stage":[68,78,102,144],"generates":[69],"a":[70,106],"segment":[71],"music.":[73,170],"The":[74,87,126],"outputs":[75],"from":[76,99,151],"are":[79,165],"then":[80],"concatenated":[81],"form":[83],"complete":[85],"composition.":[86],"first,":[88],"called":[89],"audio-prompt-guided":[91],"strategy,":[92,130],"employs":[93],"tail":[95],"audio":[97,136],"features":[98],"previous":[101,135],"serve":[104],"as":[105,138],"prefix":[107],"current":[110,124,143],"stage,":[111],"using":[112],"masking":[113],"techniques":[114],"guide":[116],"remainder":[121],"stage.":[125],"second,":[127],"structure-guided":[129],"leverages":[131],"structure":[133],"representations":[137],"intermediate":[139,153],"states":[140],"in":[141],"generation,":[145],"initiating":[146],"inference":[148],"sampling":[149],"process":[150],"time":[154],"step.":[155],"Our":[156,171],"experiments":[157],"demonstrate":[158],"that":[159],"existing":[160],"short-form":[161],"systems":[164],"capable":[166],"generating":[168],"demo":[172],"page":[173],"is":[174],"provided":[175],"at":[176],"https://longmusic.github.io/long-music/.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}