{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:39:26Z","timestamp":1792514366524,"version":"4.5.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956613","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"23-30","source":"Crossref","is-referenced-by-count":4,"title":["StyleVC: Non-Parallel Voice Conversion with Adversarial Style Generalization"],"prefix":"10.1109","author":[{"given":"In-Sun","family":"Hwang","sequence":"first","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang-Hoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Wavenet: A Generative Model for Raw Audio","author":"oord","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1226"},{"key":"ref33","article-title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","author":"chang","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054591"},{"key":"ref31","first-page":"5998","article-title":"Attention is All You Need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref30","article-title":"Starganvc+asr: Stargan-based Non-parallel Voice Conversion Regularized by Automatic Speech Recognition","author":"sakamoto","year":"2021"},{"key":"ref37","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","author":"kong","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref36","first-page":"2096","article-title":"Domain-Adversarial Training of Neural Networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref35","first-page":"3165","article-title":"Fastspeech: Fast, Robust and Controllable Text to Speech","author":"ren","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref34","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","author":"kim","year":"2021","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"13198","DOI":"10.1609\/aaai.v35i14.17559","article-title":"MultispectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis","author":"lee","year":"2021","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref1","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 (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref24","first-page":"7836","article-title":"Unsupervised Speech Decomposition via Triple Information Bottleneck","author":"qian","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref50","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0087056"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412454"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412349"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412817"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413144"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412360"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412884"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413345"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref4","article-title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","author":"choi","year":"2021","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref6","volume":"2388","author":"lee","year":"2003","journal-title":"Pattern Recognition with Support Vector Machines First International Workshop SVM 2002 Niagara Falls Canada August 10 2002 Proceedings"},{"key":"ref5","article-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"baevski","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2736600"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1109\/72.557671","article-title":"A New Recurrent Neural-Network Architecture for Visual Pattern Recognition","volume":"8","author":"lee","year":"1997","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref49","first-page":"6790","article-title":"Blow: a Single-Scale Hyper-` conditioned Flow for Non-Parallel Raw-Audio Voice Conversion","author":"serra","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2020.2966826"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref45","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation","author":"min","year":"2021","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref48","article-title":"Clova Baseline System for the Voxceleb Speaker Recognition Challenge 2020","author":"heo","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref42","article-title":"Decoupled Weight Decay Regularization","author":"loshchilov","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref43","article-title":"Superseded-cstr Vctk Corpus: English Multi-Speaker Corpus for Cstr Voice Cloning Toolkit","author":"veaux","year":"2016"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956613.pdf?arnumber=9956613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:06:20Z","timestamp":1671480380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956613","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}