{"id":"https://openalex.org/W4408352609","doi":"https://doi.org/10.1109/icassp49660.2025.10890827","title":"PicoAudio: Enabling Precise Temporal Controllability in Text-to-Audio Generation","display_name":"PicoAudio: Enabling Precise Temporal Controllability in Text-to-Audio Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352609","doi":"https://doi.org/10.1109/icassp49660.2025.10890827"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890827","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":"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/A5000223918","display_name":"Zeyu Xie","orcid":"https://orcid.org/0009-0001-9546-3301"},"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":"Zeyu Xie","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"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":"Xuenan Xu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["Shanghai AI Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"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":"Mengyue Wu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000223918"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.0102,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8914909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9972000122070312,"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":0.9972000122070312,"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":0.9825999736785889,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.8707160949707031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613997459411621},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4140147566795349},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3747900128364563},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2113608717918396},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.18959695100784302}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.8707160949707031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613997459411621},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4140147566795349},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3747900128364563},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2113608717918396},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.18959695100784302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890827","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/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2945761034","https://openalex.org/W2972478942","https://openalex.org/W3015591594","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4385245566","https://openalex.org/W4387969125","https://openalex.org/W4390873030","https://openalex.org/W4392903391","https://openalex.org/W4392910827","https://openalex.org/W4393147260","https://openalex.org/W4396877837","https://openalex.org/W4401809402","https://openalex.org/W4406461271","https://openalex.org/W6810940779","https://openalex.org/W6840815571","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6851290578","https://openalex.org/W6852971826","https://openalex.org/W6856434366","https://openalex.org/W6859583170","https://openalex.org/W6861353174"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2036697162","https://openalex.org/W2140812588","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902"],"abstract_inverted_index":{"Recently,":[0],"audio":[1,15,36,49,73,97],"generation":[2,37,50,74,120],"tasks":[3],"have":[4],"attracted":[5],"considerable":[6],"research":[7],"interests.":[8],"Despite":[9],"rapid":[10],"advancements":[11],"in":[12,105,122],"generating":[13],"high-fidelity":[14],"that":[16,98,114],"is":[17,27,32],"coarsely":[18],"aligned":[19],"with":[20,38,101],"the":[21,80,102,106,135],"text":[22,82],"description,":[23],"precise":[24],"temporal":[25,47,69,103],"controllability":[26],"still":[28],"a":[29,46],"challenge,":[30],"which":[31],"essential":[33],"to":[34,60,71],"integrate":[35],"real":[39],"applications.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"propose":[45],"controlled":[48],"framework,":[51],"PicoAudio.":[52],"It":[53],"leverages":[54],"data":[55],"crawling,":[56],"segmentation":[57],"and":[58,95,110,126],"filtering":[59],"simulate":[61],"fine-grained":[62],"temporally-aligned":[63],"audio-text":[64],"data.":[65],"Furthermore,":[66],"PicoAudio":[67,89,115],"integrates":[68],"information":[70],"guide":[72],"through":[75],"tailored":[76],"model":[77],"design.":[78],"With":[79],"effective":[81],"processing":[83],"capabilities":[84],"from":[85],"large":[86],"language":[87,93],"models,":[88],"can":[90],"take":[91],"natural":[92],"input":[94],"generate":[96],"aligns":[99],"well":[100],"description":[104],"input.":[107],"Both":[108],"subjective":[109],"objective":[111],"evaluation":[112],"demonstrate":[113],"dramatically":[116],"surpasses":[117],"current":[118],"state-of-the-art":[119],"models":[121],"terms":[123],"of":[124],"timestamp":[125],"occurrence":[127],"frequency":[128],"controllability.":[129],"Generation":[130],"samples":[131],"are":[132],"available":[133],"at":[134],"$PicoAudio":[136],"-":[137],"Demo$.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
