{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,22]],"date-time":"2024-12-22T05:04:00Z","timestamp":1734843840508,"version":"3.32.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2024,10,17]]},"DOI":"10.1109\/o-cocosda64382.2024.10800102","type":"proceedings-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T18:56:08Z","timestamp":1734720968000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Feedback-Driven Self-Improvement Strategy and Emotion-Aware Vocoder for Emotional Voice Conversion"],"prefix":"10.1109","author":[{"given":"Zhanhang","family":"Zhang","sequence":"first","affiliation":[{"name":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TASLP.2019.2892235"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP.2019.8683282"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.21437\/Interspeech.2019-2386"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Odyssey.2020-33"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.21437\/Interspeech.2020-2014"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2021-781"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TASLP.2019.2960721"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TAFFC.2022.3175578"},{"key":"ref9","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref10","article-title":"GANs trained by a two-time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems (NeurIPS"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/cvpr.2017.19"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/asru.2017.8268950"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TASLP.2022.3196879"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.5923\/j.ajsp.20120205.06"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/icis.2016.7550889"},{"key":"ref16","article-title":"Fastspeech: Fast, robust and control-lable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref18","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"ArXiv"},{"key":"ref19","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP.2014.6853678"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/icassp40776.2020.9054579"},{"key":"ref22","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edin-burgh"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1016\/j.specom.2021.11.006"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.21437\/Interspeech.2017-1386"}],"event":{"name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2024,10,17]]},"location":"Hsinchu City, Taiwan","end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799946\/10799972\/10800102.pdf?arnumber=10800102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T06:18:14Z","timestamp":1734761894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda64382.2024.10800102","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}