{"id":"https://openalex.org/W4408352448","doi":"https://doi.org/10.1109/icassp49660.2025.10889172","title":"TAGMO: Temporal Control Audio Generation for Multiple Visual Objects Without Training","display_name":"TAGMO: Temporal Control Audio Generation for Multiple Visual Objects Without Training","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352448","doi":"https://doi.org/10.1109/icassp49660.2025.10889172"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889172","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":"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/A5100390719","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0000-0003-0034-9037"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Xinyu Zhang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keyu Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Keyu Fan","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367890","display_name":"Yiran Wang","orcid":"https://orcid.org/0000-0002-5786-8789"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yiran Wang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499914","display_name":"Yingshan Liang","orcid":"https://orcid.org/0000-0003-2264-5566"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yingshan Liang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108898629","display_name":"Jiasheng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiasheng Lu","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113983572","display_name":"Zhimin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Zhicheng Du","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066253638","display_name":"Qingyang Shi","orcid":"https://orcid.org/0000-0003-4299-5889"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Qingyang Shi","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014040365","display_name":"Peiwu Qin","orcid":"https://orcid.org/0000-0002-7829-8973"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Peiwu Qin","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9818999767303467,"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":0.9818999767303467,"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":0.9805999994277954,"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":0.9099000096321106,"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/computer-science","display_name":"Computer science","score":0.8178567886352539},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.713320255279541},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7046158313751221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5329521298408508},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5253089070320129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43517446517944336},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36234474182128906},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35576069355010986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178567886352539},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.713320255279541},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7046158313751221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5329521298408508},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5253089070320129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43517446517944336},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36234474182128906},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35576069355010986},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889172","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":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2972478942","https://openalex.org/W4281736089","https://openalex.org/W4386071828","https://openalex.org/W4387969125","https://openalex.org/W4389519587","https://openalex.org/W4392909979","https://openalex.org/W4393147260","https://openalex.org/W4396877837","https://openalex.org/W4401024632","https://openalex.org/W4402727802","https://openalex.org/W4402816831","https://openalex.org/W4403780831","https://openalex.org/W4403791727","https://openalex.org/W4411245083","https://openalex.org/W6779823529","https://openalex.org/W6845479124","https://openalex.org/W6846655393","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6852971826","https://openalex.org/W6853096648","https://openalex.org/W6854445938","https://openalex.org/W6860973843","https://openalex.org/W6861363789","https://openalex.org/W6865466262","https://openalex.org/W6866562102","https://openalex.org/W6868582632","https://openalex.org/W6869582388","https://openalex.org/W6870515680"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W230091440","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"With":[0],"the":[1,65,102,110,114],"great":[2],"popularity":[3],"of":[4,71,113],"Sora,":[5],"video-based":[6],"audio":[7,45,116],"generation":[8,15,46,117],"has":[9],"become":[10],"indispensable.":[11],"While":[12],"numerous":[13],"video-to-audio":[14],"models":[16],"have":[17],"emerged,":[18],"they":[19],"frequently":[20],"face":[21],"difficulties":[22],"including":[23],"semantic":[24,135],"incompatibilities":[25],"and":[26,68,78,106,134],"synchronization":[27],"problems,":[28],"especially":[29],"in":[30],"situations":[31],"with":[32],"multiple":[33],"objects.":[34],"To":[35],"address":[36],"these":[37],"difficulties,":[38],"we":[39,94],"introduce":[40],"TAGMO,":[41],"a":[42,84,97],"novel":[43],"training-free":[44],"method":[47,129],"that":[48,127],"offers":[49],"precise":[50],"time":[51,98],"control":[52,81],"for":[53],"multi-object":[54,91],"video":[55],"scenarios.":[56],"Our":[57],"approach":[58],"first":[59],"employs":[60],"object":[61],"detection":[62],"to":[63,89,119],"obtain":[64],"class":[66],"labels":[67,70,105],"temporal":[69,104,122,131],"each":[72],"object,":[73],"which":[74],"are":[75,139],"then":[76],"structured":[77],"utilized":[79],"as":[80],"conditions":[82],"within":[83],"latent":[85],"diffusion":[86],"model":[87,118],"(LDM)":[88],"generate":[90],"audio.":[92],"Additionally,":[93],"innovatively":[95],"design":[96],"mask":[99],"based":[100],"on":[101],"corresponding":[103],"integrate":[107],"it":[108],"into":[109],"denoising":[111],"process":[112],"pre-trained":[115],"achieve":[120],"accurate":[121],"control.":[123],"Experimental":[124],"results":[125],"demonstrate":[126],"our":[128],"enhances":[130],"alignment":[132],"accuracy":[133],"consistency.":[136],"Audio":[137],"demonstrations":[138],"available":[140],"at":[141],"https://coco-create.github.io/.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
