{"id":"https://openalex.org/W4408345986","doi":"https://doi.org/10.1109/icassp49660.2025.10889879","title":"AudioTime: A Temporally-aligned Audio-text Benchmark Dataset","display_name":"AudioTime: A Temporally-aligned Audio-text Benchmark Dataset","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345986","doi":"https://doi.org/10.1109/icassp49660.2025.10889879"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889879","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":6.3913,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96207002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"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":0.9976000189781189,"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":0.9976000189781189,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9595999717712402,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7841348648071289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.768176257610321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41497015953063965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3888249397277832},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05972933769226074},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05527353286743164}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7841348648071289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768176257610321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41497015953063965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3888249397277832},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05972933769226074},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05527353286743164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889879","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2771361008","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4385822843","https://openalex.org/W4387969125","https://openalex.org/W4392910528","https://openalex.org/W4392910827","https://openalex.org/W4393147260","https://openalex.org/W4396877837","https://openalex.org/W4401809402","https://openalex.org/W4403780831","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6852971826"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,29,33,106],"audio":[3,11,24,87],"generation":[4,141],"have":[5],"enabled":[6],"the":[7,43,55,75,77,79,83,135,147],"creation":[8],"of":[9,45,57,120,139],"high-fidelity":[10],"clips":[12],"from":[13],"free-form":[14,49],"textual":[15,91],"descriptions.":[16],"However,":[17],"temporal":[18,36,70,90,107,121,136],"relation,":[19],"a":[20,58,96,126],"critical":[21],"feature":[22],"for":[23,66],"content,":[25],"is":[26,54,64],"currently":[27],"underrepresented":[28],"mainstream":[30],"models,":[31],"resulting":[32],"an":[34],"imprecise":[35],"controllability.":[37],"Specifically,":[38],"users":[39],"cannot":[40],"accurately":[41],"control":[42,137],"timestamps":[44],"sound":[46],"events":[47],"using":[48],"text.":[50],"One":[51],"significant":[52],"challenge":[53],"absence":[56],"high-quality,":[59],"temporally-aligned":[60,74,97],"audio-text":[61,98],"dataset,":[62,99],"which":[63],"essential":[65],"training":[67],"models":[68,80],"with":[69],"control.":[71,122],"The":[72],"more":[73],"annotations,":[76],"better":[78],"can":[81],"understand":[82],"precise":[84],"relationship":[85],"between":[86],"outputs":[88],"and":[89,114,130],"prompts.":[92],"Therefore,":[93],"we":[94,124],"propose":[95],"AudioTime.":[100],"It":[101],"provides":[102],"text":[103],"annotations":[104],"rich":[105],"information":[108],"such":[109],"as":[110],"timestamps,":[111],"duration,":[112],"frequency,":[113],"ordering,":[115],"covering":[116],"almost":[117],"all":[118],"aspects":[119],"Additionally,":[123],"offer":[125],"comprehensive":[127],"test":[128],"set":[129],"evaluation":[131],"metric":[132],"to":[133],"assess":[134],"performance":[138],"text-to-audio":[140],"models.":[142],"Examples":[143],"are":[144],"available":[145],"on":[146],"$AudioTime":[148],"-":[149],"Demo$.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}