{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:05:16Z","timestamp":1776888316414,"version":"3.51.2"},"reference-count":20,"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\/icassp43922.2022.9747763","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6332-6336","source":"Crossref","is-referenced-by-count":28,"title":["SpeechSplit2.0: Unsupervised Speech Disentanglement for Voice Conversion without Tuning Autoencoder Bottlenecks"],"prefix":"10.1109","author":[{"given":"Chak","family":"Ho Chan","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]},{"given":"Kaizhi","family":"Qian","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.1109\/ICCV.2017.244","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"zhu","year":"2017","journal-title":"2017 IEEE International Conference on Computer Vision (ICCV)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref14","article-title":"Global prosody style transfer without text transcriptions","author":"qian","year":"2021","journal-title":"ICML"},{"key":"ref15","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"qian","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref17","article-title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition","author":"jaitly","year":"2013","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1229"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2163"},{"key":"ref3","article-title":"VAW-GAN for disentanglement and recomposition of emotional elements in speech","author":"zhou","year":"2020","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref5","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref20","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","author":"yamagishi","year":"2019"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09747763.pdf?arnumber=9747763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:51Z","timestamp":1661199231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747763","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}