{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:28Z","timestamp":1737176848173,"version":"3.33.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832165","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"455-461","source":"Crossref","is-referenced-by-count":0,"title":["Data Efficient Reflow for Few Step Audio Generation"],"prefix":"10.1109","author":[{"given":"Lemeng","family":"Wu","sequence":"first","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Shi","sequence":"additional","affiliation":[{"name":"Meta FAIR,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gael Le","family":"Lan","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varun","family":"Nagaraja","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhao","family":"Mei","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunyang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bilge","family":"Soran","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghuraman","family":"Krishnamoorthi","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"Meta FAIR,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Shi","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikas","family":"Chandra","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kreuk","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref4","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref5","first-page":"21450","article-title":"Audioldm: text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Liu"},{"key":"ref6","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024","journal-title":"arXiv preprint arXiv:2402.04825"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref8","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023","journal-title":"arXiv preprint arXiv:2312.15821"},{"article-title":"Progressive distillation for fast sampling of diffusion models","year":"2022","author":"Salimans","key":"ref9"},{"article-title":"Latent consistency models: Synthesizing highresolution images with few-step inference","year":"2023","author":"Luo","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00783"},{"article-title":"Perflow: Accelerating diffusion models with piecewise rectified flows","year":"2024","author":"Yan","key":"ref12"},{"article-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","year":"2024","author":"Kim","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/960128.806879"},{"article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","year":"2022","author":"Lu","key":"ref15"},{"article-title":"Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models","year":"2023","author":"Lu","key":"ref16"},{"article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","year":"2022","author":"Liu","key":"ref17"},{"article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","year":"2024","author":"Liu","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445948"},{"key":"ref20","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Simple and controllable music generation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Copet","key":"ref21"},{"article-title":"Masked audio generative modeling","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ziv","key":"ref22"},{"article-title":"Flow matching for generative modeling","year":"2023","author":"Lipman","key":"ref23"},{"key":"ref24","article-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","author":"Kim","year":"2023","journal-title":"arXiv preprint arXiv:2310.02279"},{"article-title":"Bespoke solvers for generative flow models","year":"2023","author":"Shaul","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00911"},{"article-title":"Classifier-free diffusion guidance","year":"2022","author":"Ho","key":"ref27"},{"article-title":"Audiobox: Unified audio generation with natural language prompts","year":"2023","author":"Vyas","key":"ref28"},{"article-title":"High-resolution image synthesis with latent diffusion models","year":"2021","author":"Rombach","key":"ref29"},{"article-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","year":"2019","author":"Kilgour","key":"ref30"},{"article-title":"Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation","year":"2024","author":"Wu","key":"ref31"},{"article-title":"High fidelity neural audio compression","year":"2022","author":"D\u00e9fossez","key":"ref32"},{"issue":"140","key":"ref33","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832165.pdf?arnumber=10832165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:18Z","timestamp":1737100218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832165","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}