{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T20:12:35Z","timestamp":1774642355457,"version":"3.50.1"},"reference-count":23,"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\/icassp48485.2024.10446349","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"261-265","source":"Crossref","is-referenced-by-count":2,"title":["SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation"],"prefix":"10.1109","author":[{"given":"Xinlei","family":"Niu","sequence":"first","affiliation":[{"name":"Australian National University,Canberra,Australia"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Australian National University,Canberra,Australia"}]},{"given":"Christian","family":"Walder","sequence":"additional","affiliation":[{"name":"Google DeepMind,Montreal,Canada"}]},{"given":"Charles Patrick","family":"Martin","sequence":"additional","affiliation":[{"name":"Australian National University,Canberra,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref4","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2023","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413439"},{"key":"ref7","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref8","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref10","article-title":"Text-driven foley sound generation with latent diffusion model","author":"Yuan","year":"2023"},{"key":"ref11","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Song"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref14","article-title":"Make-an-audio 2: Temporalenhanced text-to-audio generation","author":"Huang","year":"2023"},{"key":"ref15","article-title":"Neural discrete representation learning","author":"Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS 2021"},{"key":"ref17","article-title":"Discrete contrastive diffusion for cross-modal music and image generation","author":"Zhu","year":"2022","journal-title":"ICLR"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations, ICLR","author":"Hu"},{"key":"ref19","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"9th ICLR"},{"key":"ref20","article-title":"Audiocaps: Generating captions for audios in the wild","author":"Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref22","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"Kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"}],"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\/10446349.pdf?arnumber=10446349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:11:29Z","timestamp":1722575489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446349","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}