{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:59:23Z","timestamp":1764403163558},"reference-count":29,"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\/icassp43922.2022.9746812","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6667-6671","source":"Crossref","is-referenced-by-count":9,"title":["HiFi-SVC: Fast High Fidelity Cross-Domain Singing Voice Conversion"],"prefix":"10.1109","author":[{"given":"Yong","family":"Zhou","sequence":"first","affiliation":[{"name":"iQIYI Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangju","family":"Lu","sequence":"additional","affiliation":[{"name":"iQIYI Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"PPG-based singing voice conversion with adversarial representation learning","year":"2020","author":"li","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428161"},{"article-title":"Wavegrad: Estimating gradients for waveform generation","year":"2020","author":"chen","key":"ref13"},{"key":"ref14","article-title":"Conformer: Convolutionaugmented transformer for speech recognition","author":"gulati","year":"2020","journal-title":"InterSpeech"},{"article-title":"FiLM: visual reasoning with a general conditioning layer","year":"2017","author":"perez","key":"ref15"},{"key":"ref16","article-title":"HiFiGAN: generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref19","first-page":"5206","article-title":"LibriSpeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref3","article-title":"CycleGAN-VC3: examining and improving cyclegan-vcs for mel-spectrogram conversion","author":"kaneko","year":"2020","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref5","article-title":"One-shot voice conversion by separating speaker and content representations with instance normalization","author":"chou","year":"2019","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"article-title":"Towards fine-grained prosody control for non-parallel voice conversion","year":"2020","author":"lian","key":"ref9"},{"article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref1"},{"key":"ref20","article-title":"Hider-Finder-Combiner: an adversarial architecture for general speech signal modification","author":"webber","year":"2020","journal-title":"InterSpeech"},{"article-title":"CSTR VCTK Corpus: english multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","year":"2019","author":"junichi","key":"ref22"},{"article-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"article-title":"SpeechBrain: A general-purpose speech toolkit","year":"2021","author":"ravanelli","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09746812.pdf?arnumber=9746812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:10:03Z","timestamp":1660579803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746812","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}