{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:49:21Z","timestamp":1761061761259,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research"},{"name":"Samsung Electronics Co., Ltd."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lsp.2022.3226655","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:29:59Z","timestamp":1670279399000},"page":"2502-2506","source":"Crossref","is-referenced-by-count":8,"title":["SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1319-8215","authenticated-orcid":false,"given":"Byoung Jin","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4689-3110","authenticated-orcid":false,"given":"Myeonghun","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}]},{"given":"Joun Yeop","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Research, Samsung Electronics Co., Ltd, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92","year":"2019","author":"yamagishi","key":"ref38"},{"key":"ref33","first-page":"10?236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume":"31","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","article-title":"Density estimation using real NVP","author":"dinh","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","article-title":"Nice: Non-linear independent components estimation","author":"dinh","year":"0","journal-title":"Proc Int Conf Mach Learn Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-441"},{"key":"ref37","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","first-page":"6793","article-title":"Blow: A single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","volume":"32","author":"serr\u00e0","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Semi-conditional normalizing flows for semi-supervised learning","author":"atanov","year":"0","journal-title":"Proc Workshop Invertible Neural Nets Normaliz Flows (ICML)"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"oord","key":"ref34"},{"key":"ref10","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"kim","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"0","journal-title":"Proc Neural Inf Process Syst Workshop Deep Learn"},{"key":"ref11","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.598807"},{"key":"ref16","article-title":"Speaker adaptation for HMM-based speech synthesis system using MLLR","author":"tamura","year":"0","journal-title":"Proc 3rd ESCA\/COCOSDA Workshop (ETRW) Speech Synth"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941037"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0181"},{"key":"ref19","first-page":"10?040","article-title":"Neural voice cloning with a few samples","volume":"31","author":"arik","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Instance normalization: The missing ingredient for fast stylization","year":"2016","author":"ulyanov","key":"ref28"},{"key":"ref4","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"ar?k","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"1705","article-title":"Adversarial speaker-consistency learning using untranscribed speech data for zero-shot multi-speaker text-to-speech","author":"choi","year":"0","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref5","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"ren","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref20","article-title":"AdaSpeech: Adaptive text to speech for custom voice","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref21","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Clova baseline system for the VoxCeleb speaker recognition challenge 2020","year":"2020","author":"heo","key":"ref42"},{"key":"ref24","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","author":"casanova","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17559"},{"article-title":"SpeechBrain: A general-purpose speech toolkit","year":"2021","author":"ravanelli","key":"ref43"},{"key":"ref25","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-speaker adaptive text-to-speech generation","author":"min","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9686799\/09969586.pdf?arnumber=9969586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:09:42Z","timestamp":1673896182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9969586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/lsp.2022.3226655","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2022]]}}}