{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T07:40:16Z","timestamp":1735026016080,"version":"3.32.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["12464060"],"award-info":[{"award-number":["12464060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10799970","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"576-580","source":"Crossref","is-referenced-by-count":0,"title":["Fast Sampling Based on Policy Gradient for Diffusion-Based Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Yubo","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University"}]},{"given":"Zhihua","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26597"},{"key":"ref4","article-title":"Dose: Dif-fusion dropout with adaptive prior for speech enhancement","volume":"36","author":"Tai","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095850"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilis-tic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Score-based generative modeling through stochas-tic differential equations","volume-title":"International Conference on Learning Representations, 2020","author":"Song","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref11","article-title":"Se-bridge: Speech enhancement with consistent brownian bridge","author":"Qiu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447860"},{"key":"ref13","first-page":"26245","article-title":"Input perturbation reduces exposure bias in diffusion models","volume-title":"International Conference on Machine Learning","author":"Ning"},{"key":"ref14","article-title":"Dif-fwave: A versatile diffusion model for audio synthesis","volume-title":"arXiv preprint","author":"Kong","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2648"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706647"},{"key":"ref17","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510583"},{"key":"ref19","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"International conference on machine learning","author":"Arjovsky"},{"key":"ref20","first-page":"1","article-title":"Empirical distributions of dft-domain speech coefficients based on estimated speech variances","volume-title":"Proc. Int. Workshop Acoust. Echo Noise Control","author":"Gerkmann"},{"key":"ref21","article-title":"Optimizing ddpm sampling with shortcut fine-tuning","author":"Fan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"High-dimensional continuous control using generalized advan-tage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"3481","article-title":"Which training methods for gans do actually converge?","volume-title":"International conference on machine learning","author":"Mescheder"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref26","first-page":"16","article-title":"Getting started with the darpa timit cd-rom: An acoustic phonetic continuous speech database","volume":"107","author":"Garofolo","year":"1988","journal-title":"National Institute of Stan-dards and Technology (NIST), Gaithersburgh, MD"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref31","article-title":"On fast sampling of diffusion probabilis-tic models","volume-title":"ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models","author":"Kong","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3040693"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10799970.pdf?arnumber=10799970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:29:04Z","timestamp":1735021744000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10799970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10799970","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}