{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:39:00Z","timestamp":1730198340686,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023357","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"125-132","source":"Crossref","is-referenced-by-count":2,"title":["Non-parallel Many-to-many Singing Voice Conversion by Adversarial Learning"],"prefix":"10.1109","author":[{"given":"Jinsen","family":"Hu","sequence":"first","affiliation":[]},{"given":"Chunyan","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Faqian","family":"Guan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref32","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"li","year":"2017","journal-title":"CoRR abs\/1705 02304"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref30","article-title":"Singing voice separation with deep u-net convolutional networks","author":"jansson","year":"0","journal-title":"Proc of ISMIR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref11","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational au-to-encoder","author":"hsu","year":"2016","journal-title":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref12","first-page":"3164","article-title":"Voice conversion from unaligned corpora using variational autoencoding Wasserstein generative adversarial networks","author":"hsu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref15","first-page":"2514","article-title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","author":"kobayashi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","first-page":"2754","article-title":"Statistical singing voice conversion based on direct waveform modification with global variance","author":"kobayashi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref19","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref28","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref27","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref6","first-page":"1","article-title":"Singing voice conversion method based on many-to-many eigenvoice conversion and training data generation using a singing-to-singing synthesis system","author":"doi","year":"2012","journal-title":"Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref5","first-page":"iv1249","article-title":"One-to-Many and Many-to-One Voice Conversion Based on Eigenvoices","author":"toda","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1295"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1662"},{"key":"ref2","first-page":"71","article-title":"GMM voice conversion of singing voice using vocal tract area function","volume":"110","author":"kawakami","year":"2010","journal-title":"IEICE technical report Speech"},{"key":"ref9","first-page":"3409","article-title":"Spectre-Temporal Modelling with Time-Frequency LSTM and Structured Output Layer for Voice Conversion","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","first-page":"2162","article-title":"Applying voice conversion to concatenative singing-voice synthesis","author":"villavicencio","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"Self-Attention Generative Adversarial Networks","author":"zhang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081710"},{"key":"ref21","article-title":"Differentiable learning-to-normalize via switchable normalization","author":"luo","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952601"},{"key":"ref26","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref25","article-title":"Which training methods for gans do actually converge?","author":"mescheder","year":"0","journal-title":"International Conference on Machine Learning (ICML)"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023357.pdf?arnumber=9023357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:48:19Z","timestamp":1658094499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023357","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}