{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:55:16Z","timestamp":1777128916646,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747664","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7237-7241","source":"Crossref","is-referenced-by-count":53,"title":["VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis"],"prefix":"10.1109","author":[{"given":"Yongmao","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cong","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"NetEase Inc,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxiao","family":"Bi","sequence":"additional","affiliation":[{"name":"NetEase Inc,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref11","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":"ref12","article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","author":"chen","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683154"},{"key":"ref16","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref17","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-414"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1789"},{"key":"ref6","article-title":"Xiaoice-Sing: A High-Quality and Integrated Singing Voice Synthesis System","author":"lu","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref1","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref9","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","author":"gomez","year":"2006","journal-title":"Proceedings of the 23rd International Conference on Machine Learning"},{"key":"ref22","article-title":"Midi manufacturers association","author":"association","year":"0"},{"key":"ref21","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"SSW 125"},{"key":"ref24","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"kim","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Density estimation using real nvp","author":"dinh","year":"2017","journal-title":"International Conference on Learning Representations"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747664.pdf?arnumber=9747664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:41Z","timestamp":1660594301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747664","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}