{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:17:36Z","timestamp":1764019056698,"version":"3.32.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800419","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"184-188","source":"Crossref","is-referenced-by-count":5,"title":["COMOSVC: Consistency Model-Based Singing Voice Conversion"],"prefix":"10.1109","author":[{"given":"Yiwen","family":"Lu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"}]},{"given":"Zhen","family":"Ye","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}]},{"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Qifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}]},{"given":"Yike","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Leveraging content-based features from multiple acoustic models for singing voice conversion","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-539"},{"article-title":"Statistical singing voice conversion based on direct wave-form modification with global variance","volume-title":"Sixteenth Annual Conference of the International Speech Communication Association","year":"2015","key":"ref3"},{"issue":"253","key":"ref4","first-page":"7","article-title":"Statistical singing voice conversion based on direct waveform modification and its parameter generation algorithms","volume-title":"IEICE Technical Report; IEICE Tech. Rep.","volume":"115","author":"Kobayashi","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1761"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428161"},{"volume-title":"Softvc vits singing voice conversion","year":"2023","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref10","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref12","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","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":"ref15","article-title":"Fast and reliable f0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech","volume-title":"Audio Engineering Soci-ety Conference: 35th International Conference: Audio for Games","author":"Morise","year":"2009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref17","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Zhang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref19","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800419.pdf?arnumber=10800419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:29:28Z","timestamp":1735021768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800419","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}