{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:12:26Z","timestamp":1761894746045,"version":"build-2065373602"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209065","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["PGD-N2L: A Parameter-Guided Disentanglement Approach for Normal-To-Lombard Speech Conversion"],"prefix":"10.1109","author":[{"given":"Hongyang","family":"Chen","sequence":"first","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}]},{"given":"Xinmeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}]},{"given":"Xingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}]},{"given":"Weiping","family":"Tu","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}]},{"given":"Cedar","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong OPPO Mobile Telecommunications Corp.,China"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Guangdong OPPO Mobile Telecommunications Corp.,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"101","article-title":"Le signe de l\u2019elevation de la voix","volume":"37","author":"Lombard","year":"1911","journal-title":"Ann. Mal. de L\u2019Oreille et du Larynx"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.3623753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.5042758"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682648"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068565"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09907-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761546"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895923"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102916"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00228"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687538"},{"article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"ICLR","author":"Popov","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref17","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"NeurIPS","volume":"34","author":"Choi","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref19","first-page":"22605","article-title":"Naturalspeech 3: zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"ICML","author":"Ju"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2011.5947347"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref24","volume":"12","author":"Van Den Oord","year":"2016","journal-title":"Wavenet: A generative model for raw audio"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"article-title":"Density estimation using real nvp","volume-title":"ICLR","author":"Dinh","key":"ref27"},{"key":"ref28","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"ICML","author":"Larsen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2856374"},{"key":"ref31","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"},{"article-title":"Speech shaped noise master audio - harvard speech corpus","year":"2019","author":"Demonte","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.1479152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"journal-title":"International Telecommunication Standardization Sector (ITU-T)","article-title":"P. 808: Subjevtive evaluation of speech quality with a crowdsoucing approach","year":"2018","key":"ref36"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209065.pdf?arnumber=11209065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:34:36Z","timestamp":1761888876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209065","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}