{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:50:58Z","timestamp":1768708258657,"version":"3.49.0"},"reference-count":23,"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\/icassp43922.2022.9747550","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6672-6676","source":"Crossref","is-referenced-by-count":16,"title":["Towards Identity Preserving Normal to Dysarthric Voice Conversion"],"prefix":"10.1109","author":[{"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bence Mark","family":"Halpern","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,Delft,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lester","family":"Phillip Violeta","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,Delft,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-168"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414869"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref14","first-page":"140","article-title":"Non-parallel Voice Conversion based on Hierarchical Latent Embedding Vector Quantized Variational Autoencoder","author":"tuan","year":"2020","journal-title":"Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref16","first-page":"6309","article-title":"Neural Discrete Representation Learning","author":"van den oord","year":"2017","journal-title":"Proc NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DSLW51110.2021.9523402"},{"key":"ref19","article-title":"The M-AILABS speech dataset","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961213"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-208"},{"key":"ref5","article-title":"An objective evaluation framework for pathological speech synthesis","author":"halpern","year":"2021","journal-title":"arXiv preprint arXiv 2107 00308"},{"key":"ref8","first-page":"5998","article-title":"Attention is All you Need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413959"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SPCOM50965.2020.9179511"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683741"},{"key":"ref23","first-page":"27403","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"}],"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\/09747550.pdf?arnumber=9747550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:49Z","timestamp":1661199109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747550","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}