{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T08:39:13Z","timestamp":1725698353013},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"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":[[2021,10,17]]},"DOI":"10.1109\/waspaa52581.2021.9632754","type":"proceedings-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T21:12:28Z","timestamp":1639429948000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["End-to-End Zero-Shot Voice Conversion Using a DDSP Vocoder"],"prefix":"10.1109","author":[{"given":"Shahan","family":"Nercessian","sequence":"first","affiliation":[{"name":"iZotope, Inc.,Cambridge,MA,USA,02139"}]}],"member":"263","reference":[{"key":"ref32","first-page":"550","article-title":"Ultra-light deep MIR by trimming lottery tickets","author":"esling","year":"0","journal-title":"Proc of the International Society for Music Information Retrieval Conference"},{"key":"ref31","first-page":"317","article-title":"Diet deep generative audio models with structured lottery","author":"esling","year":"0","journal-title":"Proc of the International Conference on Digital Audio Effects"},{"year":"0","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1587\/transinf.2015EDP7457"},{"year":"2016","author":"van den oord","journal-title":"WaveNet A Generative Model for Raw Audio","key":"ref11"},{"year":"2018","author":"kalchbrenner","journal-title":"Efficient Neural Audio Synthesis","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP.2019.8683143"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP.2018.8461368"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2019-1761"},{"key":"ref16","first-page":"6284","article-title":"FO-consistent many-to-many non-parallel voice conversion via conditional autoencoder","author":"qian","year":"0","journal-title":"Proc of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP.2019.8682298"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/Interspeech.2020-1018"},{"key":"ref19","first-page":"26","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"0","journal-title":"Proc of the International Conference on Learning Representations"},{"key":"ref28","first-page":"4879","article-title":"General-ized end-to-end loss for speaker verification","author":"wan","year":"0","journal-title":"Proc of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.23919\/EUSIPCO.2019.8903099"},{"key":"ref27","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2016","journal-title":"Edinburgh The Centre for Speech Technology Research (CSTR)"},{"key":"ref3","first-page":"266","author":"kameoka","year":"2018","journal-title":"Stargan-vc Non-parallel many-to-many voice conversion with star generative adversarial networks"},{"key":"ref6","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational au-toencoder","author":"hsu","year":"0","journal-title":"Proc of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"year":"0","key":"ref29"},{"key":"ref5","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"0","journal-title":"Proc of the International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP39728.2021.9413543"},{"key":"ref7","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"70","article-title":"Zero-shot singing voice conversion","year":"0","journal-title":"Proc of the International Society for Music Information Retrieval Confer-ence"},{"key":"ref9","first-page":"1","article-title":"Phonetic pos-teriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"0","journal-title":"Proc of the IEEE International Conference on Multimedia and Expo"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.21437\/Interspeech.2020-1889"},{"year":"2020","author":"fabbro","journal-title":"Speech synthesis and control using differentiable DSP","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Interspeech.2017-1420"},{"year":"2020","author":"mccarthy","journal-title":"HooliGAN Robust high quality neural vocoding","key":"ref21"},{"year":"1993","author":"garapolo","journal-title":"TIMIT Acoust -Phonet Continuous Speech Corpus","key":"ref24"},{"key":"ref23","article-title":"Mel-generalized cepstral analysis - a unified approach to speech spectral estimation","author":"tokuda","year":"0","journal-title":"Proc Int l Conf Spoken Language Processing"},{"key":"ref26","article-title":"Self-supervised pitch detection by inverse audio synthesis","author":"engel","year":"0","journal-title":"Proc of the International Conference on Machine Learning"},{"key":"ref25","article-title":"Fast and flexible neural audio synthesis","author":"hantrakul","year":"0","journal-title":"Proc of the International Society for Music Information Retrieval Conference"}],"event":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2021,10,17]]},"location":"New Paltz, NY, USA","end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9632687\/9632666\/09632754.pdf?arnumber=9632754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:57:42Z","timestamp":1659484662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/waspaa52581.2021.9632754","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}