{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:02:04Z","timestamp":1776884524323,"version":"3.51.2"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389779","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["A Comparative Study of Voice Conversion Models With Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023"],"prefix":"10.1109","author":[{"given":"Ryuichi","family":"Yamamoto","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reo","family":"Yoneyama","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lester Phillip","family":"Violeta","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00059"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10316"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097147"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref7","first-page":"80","article-title":"Voice conversion challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion","volume-title":"Proc. Joint Workshop for the BC and VCC","author":"Zhao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref9","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume-title":"Proc. NeurIPS","volume":"35","author":"Zhang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.140"},{"key":"ref11","article-title":"JVS-MuSiC: Japanese multispeaker singing-voice corpus","author":"Tamaru","year":"2020","journal-title":"arXiv preprint arXiv:2001.07044"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref13","first-page":"487","article-title":"PJS: Phoneme-balanced japanese singing-voice corpus","volume-title":"Proc. APSIPA ASC","author":"Koguchi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref17","article-title":"The singing voice conversion challenge 2023","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2306.14422"},{"key":"ref18","first-page":"18 003","article-title":"CONTENTVEC: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proc. ICML","author":"Qian"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3193761"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref23","first-page":"16 251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Proc. NeurIPS","volume":"34","author":"Choi"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref28","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume-title":"Proc. ICML","author":"Skerry-Ryan"},{"key":"ref29","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref30","article-title":"Adaspeech: Adaptive text to speech for custom voice","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref32","article-title":"Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim","year":"2022","journal-title":"arXiv preprint arXiv:2205.15370"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref34","article-title":"NANSY++: Unified voice synthesis with neural analysis and synthesis","volume-title":"Proc. ICLR","author":"Choi"},{"key":"ref35","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref36","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2017","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref39","article-title":"Children\u2019s song dataset for singing voice research","volume-title":"Proc. ISMIR","author":"Choi"},{"key":"ref40","article-title":"KiSing: The first open-source Mandarin singing voice synthesis corpus","author":"Shi","year":"2023"},{"key":"ref41","article-title":"JSUT corpus: Free large-scale japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv preprint arXiv:1711.00354"},{"key":"ref42","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref43","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref47","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","volume":"202","author":"Radford"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389779.pdf?arnumber=10389779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:42Z","timestamp":1706027802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389779","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}