{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:40:05Z","timestamp":1783183205983,"version":"3.54.6"},"reference-count":34,"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\/asru57964.2023.10389649","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["VITS-Based Singing Voice Conversion System with DSPGAN Post-Processing for SVCC2023"],"prefix":"10.1109","author":[{"given":"Yiquan","family":"Zhou","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent Music Entertainment,Lyra Lab,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Lei","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Music Entertainment,Lyra Lab,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The Singing Voice Conversion Challenge 2023","author":"Huang","year":"2023","journal-title":"arXiv e-prints, p. arXiv:2306.14422"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1710"},{"key":"ref4","article-title":"Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic Convolution","author":"Chen","year":"2022","journal-title":"arXiv e-prints, p. arXiv:2203.17172"},{"key":"ref5","first-page":"514","article-title":"Vaw-gan for singing voice conversion with nonparallel training data","volume-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Lu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023162"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-34"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-26"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"ref10","article-title":"Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training","author":"Guo","year":"2020","journal-title":"arXiv e-prints, p. arXiv:2012.01837"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","article-title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","author":"Baevski","year":"2019","journal-title":"arXiv e-prints, p. arXiv:1910.05453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097147"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428161"},{"key":"ref16","article-title":"A Hierarchical Speaker Representation Framework for Oneshot Singing Voice Conversion","author":"Li","year":"2022","journal-title":"arXiv e-prints, p. arXiv:2206.13762"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095105"},{"key":"ref19","first-page":"18003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Qian"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref22","first-page":"17022","article-title":"Hifigan: 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":"ref23","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref24","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref25","article-title":"LibriTTS: A Corpus Derived from LibriSpeech for Textto-Speech","author":"Zen","year":"2019","journal-title":"arXiv e-prints, p. arXiv:1904.02882"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref29","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref31","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref33","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"}],"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\/10389649.pdf?arnumber=10389649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:27Z","timestamp":1706028147000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389649","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}