{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:58:12Z","timestamp":1768075092808,"version":"3.49.0"},"reference-count":29,"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\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","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\/icassp48485.2024.10445928","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"461-465","source":"Crossref","is-referenced-by-count":1,"title":["Mtdiffusion: Multi-Task Diffusion Model With Dual-Unet for Foley Sound Generation"],"prefix":"10.1109","author":[{"given":"Anbin","family":"Qi","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,School of Information and Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Xie","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Information and Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Information and Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref2","article-title":"Neural discrete representation learning","volume-title":"Advances in neural information processing systems","volume":"30","author":"van Den Oord"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref4","first-page":"864","article-title":"Pixelsnail: An improved autoregressive generative model","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596430"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in neural information processing systems","volume":"33","author":"Ho"},{"key":"ref7","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref8","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref9","article-title":"High fidelity speech synthesis with adversarial networks","author":"Bi\u0144kowski","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref11","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref14","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017"},{"key":"ref15","article-title":"Multi-task learning as multi-objective optimization","volume-title":"Advances in neural information processing systems","volume":"31","author":"Sener"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MLCR57210.2022.00014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref19","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Advances in neural information processing systems","volume":"32","author":"Song"},{"key":"ref20","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref21","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref25","article-title":"Foley sound synthesis at the dcase 2023 challenge","author":"Choi","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref28","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong"},{"key":"ref29","article-title":"Hyu submission for the dcase 2023 task 7: Diffusion probabilistic model with adversarial training for foley sound synthesis","author":"Choi","year":"2023","journal-title":"Tech. Rep., Tech. Rep., June"}],"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\/10445928.pdf?arnumber=10445928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:29Z","timestamp":1722573449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445928","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}