{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:43:34Z","timestamp":1730231014164,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746562","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6662-6666","source":"Crossref","is-referenced-by-count":2,"title":["K-Converter: An Unsupervised Singing Voice Conversion System"],"prefix":"10.1109","author":[{"given":"Ying","family":"Zhang","sequence":"first","affiliation":[{"name":"Kwai,Beijing,P.R. China"}]},{"given":"Peng","family":"Yang","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}]},{"given":"Jinba","family":"Xiao","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}]},{"given":"Ye","family":"Bai","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}]},{"given":"Hao","family":"Che","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"514","article-title":"Vaw-gan for singing voice conversion with nonparallel training data","author":"lu","year":"2020","journal-title":"APSIPA"},{"article-title":"Paralleldata-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref11"},{"journal-title":"Acoustic theory of speech production Number 2","year":"1970","author":"fant","key":"ref12"},{"key":"ref13","first-page":"116","article-title":"Fastpitchformant: Source-filter based decomposed modeling for speech synthesis","author":"bak","year":"2021","journal-title":"InterSpeech"},{"key":"ref14","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"mcfee","year":"2015","journal-title":"Proceedings of the 14th Python in Science Conference"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00059"},{"key":"ref3","first-page":"2754","article-title":"Statistical singing voice conversion based on direct waveform modification with global variance","author":"kobayashi","year":"2015","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414137"},{"key":"ref5","first-page":"2583","article-title":"Unsupervised cross-domain singing voice conversion","author":"polyak","year":"2020","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054199"},{"key":"ref7","first-page":"2583","article-title":"Unsupervised singing voice conversion","author":"nachmani","year":"2019","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-539"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054582"},{"article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","year":"2020","author":"chen","key":"ref20"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746562.pdf?arnumber=9746562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:11:26Z","timestamp":1661184686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746562","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}