{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:39Z","timestamp":1776886419533,"version":"3.51.2"},"reference-count":24,"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"}],"funder":[{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096642","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":19,"title":["TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion"],"prefix":"10.1109","author":[{"given":"Hyun Joon","family":"Park","sequence":"first","affiliation":[{"name":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea"}]},{"given":"Seok","family":"Woo Yang","sequence":"additional","affiliation":[{"name":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea"}]},{"given":"Jin Sob","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea"}]},{"given":"Wooseok","family":"Shin","sequence":"additional","affiliation":[{"name":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea"}]},{"given":"Sung Won","family":"Han","sequence":"additional","affiliation":[{"name":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747434"},{"key":"ref24","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref23","first-page":"6199","article-title":"Parallel wave-gan: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","author":"yamamoto","year":"0","journal-title":"IEEE ICASSP 2020"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"ref11","article-title":"Mediumvc: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features","author":"gu","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref22","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref19","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref6","first-page":"7734","author":"wu","year":"2020","journal-title":"ICASSP"},{"key":"ref5","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096642.pdf?arnumber=10096642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:29:40Z","timestamp":1714066180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096642","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}