{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:25:51Z","timestamp":1767338751914,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446271","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4605-4609","source":"Crossref","is-referenced-by-count":12,"title":["FSD: An Initial Chinese Dataset for Fake Song Detection"],"prefix":"10.1109","author":[{"given":"Yuankun","family":"Xie","sequence":"first","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Lu","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenghao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Ye","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China,100024"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","year":"2020","author":"Chen","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097147"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref10","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10200"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref18","first-page":"1583","article-title":"Neural networks fail to learn periodic functions and how to fix it","volume":"33","author":"Ziyin","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-528"},{"key":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446271.pdf?arnumber=10446271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:08:20Z","timestamp":1722575300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446271","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}