{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:23:24Z","timestamp":1771064604632,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096220","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Any-to-Any Voice Conversion with F<sub>0<\/sub> and Timbre Disentanglement and Novel Timbre Conditioning"],"prefix":"10.1109","author":[{"given":"Sudheer","family":"Kovela","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Valle","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ambrish","family":"Dantrey","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref20","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Tts skins: Speaker conversion via asr","author":"polyak","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746139"},{"key":"ref1","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref16","article-title":"Bigvgan: A universal neural vocoder with large-scale training","author":"lee","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471749"},{"key":"ref18","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref9","article-title":"Hifi-vc: High quality asr-based voice conversion","author":"kashkin","year":"2022"},{"key":"ref4","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096220.pdf?arnumber=10096220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:10:01Z","timestamp":1700489401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096220","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}