{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:39:30Z","timestamp":1783183170458,"version":"3.54.6"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890068","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion"],"prefix":"10.1109","author":[{"given":"Alef Iury","family":"Ferreira","sequence":"first","affiliation":[{"name":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas Rafael","family":"Gris","sequence":"additional","affiliation":[{"name":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Augusto","family":"Da Rosa","sequence":"additional","affiliation":[{"name":"AKCIT Federal University of Goias,Goiânia,Goi\u00e1s,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederico","family":"Oliveira","sequence":"additional","affiliation":[{"name":"Federal Technological University of Paraná,Medianeira,Paran\u00e1,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edresson","family":"Casanova","sequence":"additional","affiliation":[{"name":"Federal University of Mato Grosso,Cuiabá,Mato Grosso,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafael","family":"Sousa","sequence":"additional","affiliation":[{"name":"NVIDIA,São Paulo,S\u00e3o Paulo,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnaldo","family":"Junior","sequence":"additional","affiliation":[{"name":"São Paulo State University,São Paulo,S\u00e3o Paulo,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anderson","family":"Soares","sequence":"additional","affiliation":[{"name":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arlindo Galv\u00e3o","family":"Filho","sequence":"additional","affiliation":[{"name":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref2","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054199"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746709"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389649"},{"key":"ref11","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref12","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"ref15","first-page":"18 003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref16","article-title":"A unified model for zero-shot singing voice conversion and synthesis","volume-title":"Ismir 2022 Hybrid Conference","author":"Wu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-847"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389750"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-528"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/4189781"},{"key":"ref23","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40498-6_17"},{"key":"ref27","article-title":"JVS Corpus: free japanese multi-speaker voice corpus","author":"Takamichi","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref30","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref31","first-page":"9","article-title":"NHSS: A speech and singing parallel database","volume-title":"Speech Communication","volume":"133","author":"Sharma","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.549"},{"key":"ref35","article-title":"DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis","author":"Liu","year":"2021"},{"key":"ref36","first-page":"468","article-title":"VocalSet: A singing voice dataset","author":"Wilkins","year":"2018","journal-title":"ISMIR"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations","author":"Kingma"},{"key":"ref38","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1201\/9780429246593"},{"key":"ref40","article-title":"Confidence intervals for evaluation in machine learning","volume-title":"Computer Software","author":"Ferrer"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890068.pdf?arnumber=10890068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:55Z","timestamp":1774416115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890068","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}