{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:45Z","timestamp":1775230005126,"version":"3.50.1"},"reference-count":36,"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\/iscslp63861.2024.10799952","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"289-293","source":"Crossref","is-referenced-by-count":2,"title":["A Systematic Exploration of Joint-Training for Singing Voice Synthesis"],"prefix":"10.1109","author":[{"given":"Yuning","family":"Wu","sequence":"first","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qian","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/3680822"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref3","article-title":"Vocaloid-commercial singing syn-thesizer based on sample concatenation","author":"Kenmochi","year":"2007","journal-title":"Interspeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref6","article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683154"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053944"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1575"},{"key":"ref14","article-title":"We singer: Data-augmented singing voice synthesis with auxiliary losses","volume-title":"arXiv preprint","author":"Zhang","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414043"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596184"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-239"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-2360","article-title":"Toksing: Singing voice synthesis based on discrete tokens","volume-title":"ArXiv","author":"Wu","year":"2024"},{"key":"ref20","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NeurIPS","author":"Kong","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547854"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688029"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10294"},{"key":"ref28","article-title":"Espnet2-tts: Extending the edge of tts research","volume-title":"ArXiv","volume":"abs\/2110.07840","author":"Hayashi","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-277"},{"key":"ref31","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":"ref32","volume-title":"DB Production: Fu-ton P","author":"Futon","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414348"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"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\/10799952.pdf?arnumber=10799952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:42:09Z","timestamp":1735022529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10799952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10799952","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}