{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:28:02Z","timestamp":1757456882843,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3277786","type":"journal-article","created":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T17:31:48Z","timestamp":1684431108000},"page":"593-597","source":"Crossref","is-referenced-by-count":9,"title":["SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6331-2437","authenticated-orcid":false,"given":"Hyungchan","family":"Yoon","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7718-4958","authenticated-orcid":false,"given":"Changhwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2229-6741","authenticated-orcid":false,"given":"Seyun","family":"Um","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2849-4140","authenticated-orcid":false,"given":"Hyun-Wook","family":"Yoon","sequence":"additional","affiliation":[{"name":"Clova Voice, Naver Corp, Seongnam, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6554-0783","authenticated-orcid":false,"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref12","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref15","first-page":"2709","article-title":"Your TTS: 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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"article-title":"Speechbrain: A general-purpose speech toolkit","year":"2021","author":"ravanelli","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref11","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3226655"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","first-page":"10970","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech synthesis","author":"huang","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-901"},{"key":"ref19","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref18","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"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref26","article-title":"Density estimation using real NVP","author":"dinh","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref22","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref27","first-page":"7964","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref8","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref4","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"0","journal-title":"Proc 33rd Neural Inf Process Syst"},{"key":"ref6","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc 9th ISCA Workshop Speech Synthesis Workshop (SSW 9)"},{"key":"ref5","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10036333\/10129023.pdf?arnumber=10129023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:34:41Z","timestamp":1686594881000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10129023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3277786","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2023]]}}}