{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:27:27Z","timestamp":1753601247829,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448441","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1091-1095","source":"Crossref","is-referenced-by-count":4,"title":["A Detailed Audio-Text Data Simulation Pipeline Using Single-Event Sounds"],"prefix":"10.1109","author":[{"given":"Xuenan","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Xiaohang","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Zeyu","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Pingyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/WASPAA.2017.8170058"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP49357.2023.10096643"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2021-2227"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref8","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL","author":"Kim"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref10","first-page":"90","article-title":"Diversity and bias in audio captioning datasets","volume-title":"Proc. DCASE","author":"Martin"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/3581783.3613820"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/taslp.2024.3419446"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP49357.2023.10097117"},{"year":"2023","author":"Huang","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2023-1614"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/2502081.2502245"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/Interspeech.2022-10451"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICASSP.2017.7952261"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSPW59220.2023.10192960"},{"key":"ref22","article-title":"The SJTU system for DCASE2022 challenge task 6: Audio captioning with audio-text retrieval pre-training","volume-title":"DCASE2022 Challenge, Tech. Rep.","author":"Xu","year":"2022"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448441.pdf?arnumber=10448441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:53:57Z","timestamp":1722660837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448441","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}