{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:06:11Z","timestamp":1784210771422,"version":"3.55.0"},"reference-count":29,"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\/asru57964.2023.10389621","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":8,"title":["QUICKVC: A Lightweight VITS-Based Any-to-Many Voice Conversion Model using ISTFT for Faster Conversion"],"prefix":"10.1109","author":[{"given":"Houjian","family":"Guo","sequence":"first","affiliation":[{"name":"Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoran","family":"Liu","sequence":"additional","affiliation":[{"name":"Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos Toshinori","family":"Ishi","sequence":"additional","affiliation":[{"name":"Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref2","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414137"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2009.5372889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066047"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414788"},{"key":"ref13","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref15","first-page":"1021","article-title":"Real-Time, Full-Band, Online DNN-Based Voice Conversion System Using a Single CPU","volume-title":"Proc. Interspeech 2020","author":"Saeki"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095296"},{"key":"ref17","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"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 Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref25","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"International Conference on Learning Representations","author":"Popov"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3461615.3491106"},{"issue":"1","key":"ref29","first-page":"3221","article-title":"Accelerating t-sne using tree-based algorithms","volume":"15","author":"Der Maaten","year":"2014","journal-title":"The journal of machine learning research"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"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\/10389621.pdf?arnumber=10389621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:30Z","timestamp":1706027730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389621","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}