{"id":"https://openalex.org/W4415539713","doi":"https://doi.org/10.1145/3746027.3755170","title":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","display_name":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539713","doi":"https://doi.org/10.1145/3746027.3755170"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Yuxuan Jiang","orcid":"https://orcid.org/0009-0003-7134-7810"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxuan Jiang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China and Shengshu AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7134-7810","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China and Shengshu AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061402916","display_name":"Zehua Chen","orcid":"https://orcid.org/0009-0000-2294-7447"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China and Shengshu AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2294-7447","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China and Shengshu AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073017662","display_name":"Zeqian Ju","orcid":null},"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":"Zeqian Ju","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-8573-8536","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang Li","orcid":"https://orcid.org/0009-0006-7902-3759"},"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":"Chang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China and Shengshu AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7902-3759","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China and Shengshu AI, Beijing, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473085","display_name":"Weibei Dou","orcid":"https://orcid.org/0000-0001-8555-2776"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibei Dou","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8555-2776","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China and Shengshu AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6254-2388","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China and Shengshu AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.0945,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96721061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9871","last_page":"9880"},"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":0.9980000257492065,"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":0.9947999715805054,"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/quality","display_name":"Quality (philosophy)","score":0.5302000045776367},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.3952000141143799},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3752000033855438},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.35120001435279846},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097000122070312},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2784000039100647}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7525196029","display_name":null,"funder_award_id":"62376131","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":7,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W3015371781","https://openalex.org/W4205689591","https://openalex.org/W4372260310","https://openalex.org/W4381786045","https://openalex.org/W4390872297"],"related_works":[],"abstract_inverted_index":{"Text-to-audio":[0],"(T2A)":[1],"generation":[2,186],"has":[3],"achieved":[4],"promising":[5],"results":[6],"with":[7,119,188],"the":[8,17,32,86,127,194],"recent":[9],"advances":[10],"in":[11],"generative":[12],"models.":[13],"However,":[14],"because":[15],"of":[16,22],"limited":[18],"quality":[19,69,170,187],"and":[20,100,116,130,153,174,192],"quantity":[21],"temporally-aligned":[23],"audio-text":[24],"pairs,":[25],"existing":[26],"T2A":[27,64,82,93,168,199],"methods":[28,173],"struggle":[29],"to":[30,60,89,111,177],"handle":[31],"complex":[33],"text":[34,129],"prompts":[35],"that":[36],"contain":[37],"precise":[38,143],"timing":[39,55,131,144],"control,":[40],"e.g.,":[41,95],"owl":[42,96],"hooted":[43,97],"at":[44,98,103],"2.4s-5.2s.":[45],"Recent":[46],"works":[47],"have":[48],"explored":[49],"data":[50],"augmentation":[51],"techniques":[52],"or":[53],"introduced":[54],"conditions":[56],"as":[57],"model":[58],"inputs":[59],"enable":[61,90],"timing-conditioned":[62,167],"10-second":[63],"generation,":[65,94],"while":[66],"their":[67],"synthesis":[68,169],"is":[70,175],"still":[71],"limited.":[72],"In":[73],"this":[74],"work,":[75],"we":[76,106,134],"propose":[77],"a":[78,120],"novel":[79],"training-free":[80,172],"timing-controlled":[81,91,197],"framework,":[83],"FreeAudio,":[84],"making":[85],"first":[87,107],"attempt":[88],"long-form":[92,185,198],"2.4s-5.2s":[99],"crickets":[101],"chirping":[102],"0s-24s.":[104],"Specifically,":[105],"employ":[108],"an":[109],"LLM":[110],"plan":[112],"non-overlapping":[113],"time":[114],"windows":[115],"recaption":[117],"each":[118],"refined":[121],"natural":[122],"language":[123],"description,":[124],"based":[125],"on":[126],"input":[128],"prompts.":[132],"Then":[133],"introduce:":[135],"1)":[136,163],"Decoupling":[137],"&":[138],"Aggregating":[139],"Attention":[140],"Control":[141],"for":[142,150,156,196],"control;":[145],"2)":[146,181],"Contextual":[147],"Latent":[148],"Composition":[149],"local":[151],"smoothness":[152],"Reference":[154],"Guidance":[155],"global":[157],"consistency.":[158],"Extensive":[159],"experiments":[160],"show":[161],"that:":[162],"FreeAudio":[164,182],"achieves":[165],"state-of-the-art":[166],"among":[171],"comparable":[176,184],"leading":[178],"training-based":[179,189],"methods;":[180],"demonstrates":[183],"Stable":[190],"Audio":[191],"paves":[193],"way":[195],"synthesis.":[200],"Demo":[201],"samples":[202],"are":[203],"available":[204],"at:":[205],"https://freeaudio.github.io/FreeAudio/.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-25T00:00:00"}