{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:56:56Z","timestamp":1764399416385,"version":"3.46.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249129","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1104-1109","source":"Crossref","is-referenced-by-count":0,"title":["DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement"],"prefix":"10.1109","author":[{"given":"Minghui","family":"Wu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueling","family":"Liu","sequence":"additional","affiliation":[{"name":"iFlytek Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahuan","family":"Fan","sequence":"additional","affiliation":[{"name":"iFlytek Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Tang","sequence":"additional","affiliation":[{"name":"iFlytek Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Motor speech disorders: Substrates, differential diagnosis, and management","year":"2012","author":"Duffy","key":"ref1"},{"key":"ref2","first-page":"273","article-title":"Disorders of communication: Dysarthria","volume-title":"Handbook of clinical neurology","volume":"110","author":"Enderby","year":"2013"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.21437\/Interspeech.2018-1751"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.3390\/electronics12204278"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1016\/j.eswa.2015.01.033"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.3389\/fcomp.2022.770210"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1080\/10400435.2010.483646"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1044\/2024_JSLHR-23-00740"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP43922.2022.9746585"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/interspeech.2025-2155"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.21437\/Interspeech.2024-1645"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSPW65056.2025.11011033"},{"key":"ref13","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International conference on machine learning","author":"Popov","year":"2021"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/3503161.3547855"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","article-title":"Bigvgan: A universal neural vocoder with largescale training","author":"Lee","year":"2022","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/3581783.3612061"},{"key":"ref21","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2022","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TVCG.2012.291"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1186\/s13636-024-00349-3"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref27","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Wang","year":"2018"},{"key":"ref28","first-page":"10970","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Huang","year":"2022"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/s10579-011-9145-0"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","first-page":"63","article-title":"Synthesizer voice quality of new languages calibrated with mean mel cepstral distortion","author":"Kominek","year":"2008","journal-title":"SLTU"},{"key":"ref32","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ACII.2013.58"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249129.pdf?arnumber=11249129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:54:13Z","timestamp":1764399253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249129","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}