{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:08:54Z","timestamp":1776884934469,"version":"3.51.2"},"reference-count":28,"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\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","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\/icassp49357.2023.10097120","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":17,"title":["Multi-Speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit Prediction"],"prefix":"10.1109","author":[{"given":"Kevin","family":"Scheck","sequence":"first","affiliation":[{"name":"University of Bremen,Cognitive Systems Lab,Bremen,Germany"}]},{"given":"Tanja","family":"Schultz","sequence":"additional","affiliation":[{"name":"University of Bremen,Cognitive Systems Lab,Bremen,Germany"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s22166056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-229"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2752365"},{"key":"ref17","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747427"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-379"},{"key":"ref18","article-title":"The LJ Speech Dataset","author":"ito","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-388"},{"key":"ref23","article-title":"Robust speech recognition via large-scale weak supervision","author":"radford","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref20","first-page":"17022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"3976","DOI":"10.21437\/Interspeech.2017-479","article-title":"Bias and Statistical Significance in Evaluating Speech Synthesis with Mean Opinion Scores","author":"rosenberg","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci12070818"},{"key":"ref9","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume":"97","author":"qian","year":"2019","journal-title":"Proc ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738568"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7590843"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.23"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.445"}],"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\/10097120.pdf?arnumber=10097120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:02:40Z","timestamp":1699902160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097120","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}