{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:46:49Z","timestamp":1757314009003},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096399","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["LIMI-VC: A Light Weight Voice Conversion Model with Mutual Information Disentanglement"],"prefix":"10.1109","author":[{"given":"Liangjie","family":"Huang","sequence":"first","affiliation":[{"name":"Beijing Language and Culture University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Yuan","sequence":"additional","affiliation":[{"name":"Baidu (China) Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunming","family":"Liang","sequence":"additional","affiliation":[{"name":"Baidu (China) Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Baidu (China) Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Wen","sequence":"additional","affiliation":[{"name":"Baidu (China) Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanlu","family":"Xie","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengfeng","family":"Ke","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Efficient non-autoregressive gan voice conversion using vqwav2vec features and dynamic convolution","year":"2022","author":"chen","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"article-title":"Depthwise separable convolutions for neural machine translation","year":"2017","author":"kaiser","key":"ref15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref10","first-page":"1779","article-title":"Club: A contrastive log-ratio upper bound of mutual information","author":"cheng","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref2","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"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit","year":"2017","author":"macdonald","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"article-title":"Towards achieving robust universal neural vocoding","year":"2018","author":"lorenzo-trueba","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"article-title":"Deep variational information bottleneck","year":"2016","author":"alemi","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref9","first-page":"5171","article-title":"On variational bounds of mutual information","author":"poole","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747763"},{"key":"ref3","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"qian","year":"2020","journal-title":"International Conference on Machine Learning"},{"article-title":"Meta-voice: Fast few-shot style transfer for expressive voice cloning using meta learning","year":"2021","author":"liu","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-571"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096399.pdf?arnumber=10096399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:31Z","timestamp":1700507311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096399","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}