{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:56:11Z","timestamp":1776887771363,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447835","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11676-11680","source":"Crossref","is-referenced-by-count":2,"title":["Posterior Variance-Parameterised Gaussian Dropout: Improving Disentangled Sequential Autoencoders for Zero-Shot Voice Conversion"],"prefix":"10.1109","author":[{"given":"Yin-Jyun","family":"Luo","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Dixon","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref2","article-title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","volume-title":"NeurIPS","author":"Hsu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747345"},{"key":"ref4","article-title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","volume-title":"NeurIPS","author":"Jia"},{"key":"ref5","article-title":"Sample Efficient Adaptive Text-to-Speech","volume-title":"ICLR","author":"Chen"},{"key":"ref6","article-title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","volume-title":"ICLR","author":"Hsu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref8","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","volume-title":"ICML","author":"Qian"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1936"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022787"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3193761"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2086"},{"key":"ref18","article-title":"Improving Zero-Shot Voice Style Transfer via Disentangled Representation Learning","volume-title":"ICLR","author":"Yuan"},{"key":"ref19","article-title":"Disentangled Sequential Autoencoder","volume-title":"ICML","author":"Li"},{"key":"ref20","article-title":"Contrastively Disentangled Sequential Variational Autoencoder","volume-title":"NeurIPS","author":"Bai"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683131"},{"key":"ref22","article-title":"Auto-Encoding Variational Bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref23","article-title":"Recent Advances in Autoencoder-Based Representation Learning","volume-title":"NeurIPS Workshop on Bayesian Deep Learning","author":"Tschannen"},{"key":"ref24","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume-title":"JMLR","author":"Srivastava"},{"key":"ref25","article-title":"Gaussian Dropout as an Information Bottleneck Layer","volume-title":"NeurIPS Workshop on Bayesian Deep Learning","author":"Rey"},{"key":"ref26","article-title":"Fast Dropout Training","volume-title":"ICML","author":"Wang"},{"key":"ref27","article-title":"\u03b2-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework","volume-title":"ICLR","author":"Higgins"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref30","article-title":"Neural Discrete Representation Learning","volume-title":"NeurIPS","author":"van den Oord"},{"key":"ref31","article-title":"The Information Bottleneck Method","volume-title":"Allerton Conference on Communication, Control and Computation","author":"Tishby"},{"key":"ref32","article-title":"Deep Variational Information Bottleneck","volume-title":"ICLR","author":"Alemi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-26"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383498"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref38","article-title":"On the Convergence of Adam and Beyond","volume-title":"ICLR","author":"Reddi"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref40","article-title":"Importance Weighted Autoencoders","volume-title":"ICLR","author":"Burda"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447835.pdf?arnumber=10447835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:30:46Z","timestamp":1722573046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447835","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}