{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T19:38:20Z","timestamp":1783885100323,"version":"3.55.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096239","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":13,"title":["NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit"],"prefix":"10.1109","author":[{"given":"Ryuichi","family":"Yamamoto","sequence":"first","affiliation":[{"name":"LINE Corp.,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reo","family":"Yoneyama","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","volume":"32","author":"Paszke"},{"key":"ref2","volume-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"issue":"175","key":"ref3","first-page":"12","article-title":"The HTK book","volume":"3","author":"Young","year":"2002","journal-title":"Cambridge university engineering department"},{"key":"ref4","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. ASRU","author":"Povey"},{"key":"ref5","first-page":"294","article-title":"The HMM-based speech synthesis system (HTS) version 2.0","volume-title":"Proc. SSW","volume":"6","author":"Zen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref7","article-title":"Recent development of the HMM-based singing voice synthesis system\u2014Sinsy","volume-title":"Seventh ISCA Workshop on Speech Synthesis","author":"Oura"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414348"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1563"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1575"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11130"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2058.003.0010"},{"key":"ref22","volume-title":"Ameya\/Ayame, UTAU"},{"key":"ref23","volume-title":"Open singing synthesis platform \/ open source UTAU successor"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ECEI53102.2022.9829508"},{"key":"ref25","volume-title":"The original support for English NNSVS dataset creation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-67"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076805"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"ref31","article-title":"Mixture density networks","author":"Bishop","year":"1994","journal-title":"Tech. Rep."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref33","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Proc. ICML","author":"Nair"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.11.002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref38","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NeurIPS","volume":"27","author":"Goodfellow"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref40","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref41","volume-title":"[NamineRitsu] Blue (YOASOBI) [ENUNU model Ver.2, Singing DBVer.2 release]"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref44","volume-title":"DiffSinger: Singing voice synthesis via shallow diffusion mechanism","author":"Jinglin"},{"key":"ref45","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096239.pdf?arnumber=10096239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:48:52Z","timestamp":1709246932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096239","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}