{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:23:54Z","timestamp":1768073034571,"version":"3.49.0"},"reference-count":27,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446906","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"411-415","source":"Crossref","is-referenced-by-count":1,"title":["Environmental Sound Synthesis from Vocal Imitations and Sound Event Labels"],"prefix":"10.1109","author":[{"given":"Yuki","family":"Okamoto","sequence":"first","affiliation":[{"name":"Ritsumeikan University,Japan"}]},{"given":"Keisuke","family":"Imoto","sequence":"additional","affiliation":[{"name":"Doshisha University,Japan"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Ryotaro","family":"Nagase","sequence":"additional","affiliation":[{"name":"Ritsumeikan University,Japan"}]},{"given":"Takahiro","family":"Fukumori","sequence":"additional","affiliation":[{"name":"Ritsumeikan University,Japan"}]},{"given":"Yoichi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Ritsumeikan University,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683727"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1944745.1944755"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096517"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268730"},{"key":"ref14","article-title":"AudioGen: Textually guided audio generation","volume-title":"Proc. International Conference on Learning Representation (ICLR)","author":"Kreuk"},{"key":"ref15","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702387"},{"key":"ref17","first-page":"148","article-title":"Vocal imitation set: a dataset of vocally imitated sound events using the audioset ontology","volume-title":"Proc. Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2868428"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654880"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581754.3584139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-981"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref25","first-page":"1336","article-title":"On Generative Spoken Language Modeling from Raw Audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref26","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. International Conference on Learning Representation (ICLR)","author":"Liu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10446906.pdf?arnumber=10446906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:27:21Z","timestamp":1722576441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446906","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}