{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:13:00Z","timestamp":1784178780289,"version":"3.55.0"},"reference-count":20,"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\/icassp48485.2024.10446869","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1081-1085","source":"Crossref","is-referenced-by-count":16,"title":["Investigating Personalization Methods in Text to Music Generation"],"prefix":"10.1109","author":[{"given":"Manos","family":"Plitsis","sequence":"first","affiliation":[{"name":"Athena Research Center,Institute for Language and Speech Processing,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodoros","family":"Kouzelis","sequence":"additional","affiliation":[{"name":"Athena Research Center,Institute for Language and Speech Processing,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Paraskevopoulos","sequence":"additional","affiliation":[{"name":"Athena Research Center,Institute for Language and Speech Processing,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vassilis","family":"Katsouros","sequence":"additional","affiliation":[{"name":"Athena Research Center,Institute for Language and Speech Processing,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yannis","family":"Panagakis","sequence":"additional","affiliation":[{"name":"University of Athens,Department of Informatics and Telecommunications,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref2","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref3","author":"Gu","year":"2023","journal-title":"A systematic survey of prompt engineering on vision-language foundation models"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref5","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1447"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in neural information processing systems","volume":"33","author":"Ho"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053442"},{"key":"ref15","year":"2020","journal-title":"Loudness normalisation and permitted maximum level of audio signals"},{"key":"ref16","article-title":"Difference between the ebu r-128 meter recommendation and human subjective loudness perception","author":"Begnert","year":"2011","journal-title":"Audio Engineering Society Convention 131. Audio Engineering Society"},{"key":"ref17","article-title":"Automatic chord-scale recognition using harmonic pitch class profiles","volume-title":"Proceedings of the 16th Sound & Music Computing Conference; 2019 May 28-31; M\u00f3laga, Spain.[M\u00f3laga]: SMC; 2019. Sound & Music Computing Conference","author":"Demirel"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"}],"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\/10446869.pdf?arnumber=10446869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:50Z","timestamp":1722576410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446869","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}