{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:21:43Z","timestamp":1753600903963,"version":"3.33.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832285","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"675-681","source":"Crossref","is-referenced-by-count":1,"title":["Instructsing: High-Fidelity Singing Voice Generation Via Instructing Yourself"],"prefix":"10.1109","author":[{"given":"Chang","family":"Zeng","sequence":"first","affiliation":[{"name":"National Insitute of Informatics,Japan"}]},{"given":"Chunhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Geely,China"}]},{"given":"Xiaoxiao","family":"Miao","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology,Singapore"}]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Geely,China"}]},{"given":"Zhonglin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Geely,China"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Geely,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-119"},{"key":"ref3","first-page":"21450","article-title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-349"},{"key":"ref5","article-title":"HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2009.01776"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389702"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095919"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10446"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095298"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10994"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-4399-5_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-517"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11130"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"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"},{"article-title":"DDSP: Differentiable Digital Signal Processing","volume-title":"International Conference on Learning Representations","author":"Engel","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/3680788"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-32576-7"},{"key":"ref25","first-page":"234","article-title":"UNet: Convolutional Networks for Biomedical Image Segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference","author":"Ronneberger"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096724"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547854"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095557"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref32","article-title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","volume-title":"NIPS 2014 Workshop on Deep Learning","author":"Chung","key":"ref33"},{"key":"ref34","first-page":"125","article-title":"WaveNet: A Generative Model for Raw Audio","volume-title":"The 9th ISCA Speech Synthesis Workshop","volume":"2016","author":"van"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670285"},{"article-title":"Learning Normality is Enough: A Software-based Mitigation Against Inaudible Voice Attacks","volume-title":"32nd USENIX Security Symposium","author":"Li","key":"ref36"},{"key":"ref37","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-174"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref41"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832285.pdf?arnumber=10832285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:56Z","timestamp":1737101696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832285","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}