{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:03:39Z","timestamp":1756771419849,"version":"3.44.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683204","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"2777-2781","source":"Crossref","is-referenced-by-count":6,"title":["Adversarially Trained Autoencoders for Parallel-data-free Voice Conversion"],"prefix":"10.1109","author":[{"given":"Orhan","family":"Ocal","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, USA"}]},{"given":"Oguz H.","family":"Elibol","sequence":"additional","affiliation":[{"name":"Intel AI Lab, Santa Clara, USA"}]},{"given":"Gokce","family":"Keskin","sequence":"additional","affiliation":[{"name":"Intel AI Lab, Santa Clara, USA"}]},{"given":"Cory","family":"Stephenson","sequence":"additional","affiliation":[{"name":"Intel AI Lab, Santa Clara, USA"}]},{"given":"Anil","family":"Thomas","sequence":"additional","affiliation":[{"name":"Intel AI Lab, Santa Clara, USA"}]},{"given":"Kannan","family":"Ramchandran","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, USA"}]}],"member":"263","reference":[{"article-title":"Mine: mutual information neural estimation","year":"2018","author":"belghazi","key":"ref10"},{"article-title":"English multi-speaker corpus for CSTR voice cloning toolkit","year":"2012","author":"yamagishi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/1745691610393980"},{"year":"1999","key":"ref16","article-title":"Subjective video quality assessment methods for multimedia applications"},{"article-title":"Deep voice 2: Multi-speaker neural text-to-speech","year":"2017","author":"arik","key":"ref17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref6","first-page":"465","article-title":"Toward multimodal image-to-image translation","author":"zhu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref8"},{"key":"ref7","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"3","article-title":"Autoencoders, minimum description length and helmholtz free energy","author":"hinton","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)90054-3"},{"article-title":"A universal music translation network","year":"2018","author":"mor","key":"ref9"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683204.pdf?arnumber=8683204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:14:36Z","timestamp":1756754076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683204","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}