{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:48:26Z","timestamp":1765039706296,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389748","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data"],"prefix":"10.1109","author":[{"given":"Yusheng","family":"Tian","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong SAR"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong SAR"}]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong SAR"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2648"},{"key":"ref4","article-title":"Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model","author":"Sarfjoo","year":"2019","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-30"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022766"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413934"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2688"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11026"},{"key":"ref13","article-title":"Universal speech enhancement with score-based diffusion","volume":"abs\/2206.03065","author":"Serr\u00e0","year":"2022","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1889"},{"key":"ref17","first-page":"659","article-title":"A study on speech enhancement based on diffusion probabilistic model","volume-title":"Proc. APSIPA ASC","author":"Lu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song","key":"ref21"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref23","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. NeurIPS","volume":"35","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-409"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037802"},{"key":"ref26","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref29","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00101-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3038"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953152"},{"article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref33"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389748.pdf?arnumber=10389748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:23Z","timestamp":1706027783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389748","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}