{"id":"https://openalex.org/W4402979885","doi":"https://doi.org/10.1109/icme57554.2024.10687830","title":"Controllable Text-to-Audio Generation with Training-Free Temporal Guidance Diffusion","display_name":"Controllable Text-to-Audio Generation with Training-Free Temporal Guidance Diffusion","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979885","doi":"https://doi.org/10.1109/icme57554.2024.10687830"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5093854346","display_name":"Tianjiao Du","orcid":null},"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":"Tianjiao Du","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115587837","display_name":"Jun Chen","orcid":"https://orcid.org/0009-0003-1494-1418"},"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 Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108898629","display_name":"Jiasheng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiasheng Lu","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012045783","display_name":"Qinmei Xu","orcid":"https://orcid.org/0000-0001-7200-0817"},"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":"Qinmei Xu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083413053","display_name":"Huan Liao","orcid":"https://orcid.org/0009-0006-9895-7995"},"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":"Huan Liao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742729","display_name":"Yupeng Chen","orcid":"https://orcid.org/0000-0003-1605-9480"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Chen","raw_affiliation_strings":["South University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South University of Science and Technology of China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"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":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T12031","display_name":"Speech and dialogue systems","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.977400004863739,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9689000248908997,"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":0.6537404656410217},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6075322031974792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.567755937576294},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5450222492218018},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05439296364784241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6537404656410217},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6075322031974792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.567755937576294},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5450222492218018},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05439296364784241},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/icme57554.2024.10687830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2959539607","https://openalex.org/W2972478942","https://openalex.org/W3015190346","https://openalex.org/W3153469116","https://openalex.org/W3162999565","https://openalex.org/W4312933868","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4386076027","https://openalex.org/W4387969125","https://openalex.org/W4390873054","https://openalex.org/W4393147260","https://openalex.org/W4393148714"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2376932109"],"abstract_inverted_index":{"The":[0],"controllability":[1],"of":[2,13,20,37,52,83,129,145],"text-to-audio":[3],"(TTA)":[4],"systems":[5],"is":[6],"constrained":[7],"due":[8],"to":[9,18,30,40,106],"the":[10,42,61,79,98,107,120,125,135,139,146],"exclusive":[11],"generation":[12,73,143],"audio":[14,44],"from":[15],"text,":[16,136],"leading":[17],"issues":[19],"temporal":[21,76,109,114],"disorganization":[22],"and":[23,55,81,127,141],"semantic":[24],"omission.":[25],"Some":[26],"studies":[27],"have":[28],"endeavored":[29],"integrate":[31],"conditions,":[32,110],"such":[33],"as":[34,132],"frame-level":[35],"annotation":[36],"sound":[38,85,130],"events,":[39],"regulate":[41],"generated":[43,100],"content.":[45],"However,":[46],"this":[47],"necessitates":[48],"a":[49,66],"substantial":[50],"amount":[51],"paired":[53],"data":[54],"time":[56],"for":[57,70],"fine-tuning":[58],"or":[59],"training":[60],"model.":[62],"This":[63],"paper":[64],"introduces":[65],"novel,":[67],"training-free":[68],"approach":[69,95,122],"controllable":[71],"TTA":[72,103],"based":[74],"on":[75],"condition,":[77],"e.g.,":[78],"location":[80],"duration":[82],"corresponding":[84],"events.":[86],"Through":[87],"updating":[88],"latent":[89],"variables":[90],"during":[91],"inference":[92],"process,":[93],"our":[94],"ensures":[96],"that":[97,119],"content":[99],"by":[101,134],"pretrained":[102],"models":[104],"adheres":[105],"specified":[108],"thereby":[111],"achieving":[112],"precise":[113],"control.":[115],"Experimental":[116],"results":[117],"affirm":[118],"proposed":[121],"effectively":[123],"governs":[124],"initiation":[126],"conclusion":[128],"events":[131],"indicated":[133],"while":[137],"preserving":[138],"high-quality":[140],"diverse":[142],"capabilities":[144],"diffusion":[147],"model":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}