{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:43Z","timestamp":1738128463844,"version":"3.33.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849014","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["VietSing: A High-quality Vietnamese Singing Voice Corpus"],"prefix":"10.1109","author":[{"given":"Minh","family":"Vu","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2R),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binit","family":"Bhattarai","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kah Kuan","family":"Teh","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tran","family":"Huy Dat","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref2","first-page":"17 022","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":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-391"},{"article-title":"Singing voice synthesis based on convolutional neural networks","year":"2019","author":"Nakamura","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref8","first-page":"8067","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-48"},{"key":"ref14","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"author":"Tamaru","key":"ref15","article-title":"Jvs-music: Japanese multispeaker singing-voice corpus. arxiv 2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.140"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03391"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"issue":"9\/10","key":"ref19","first-page":"341","article-title":"Speak and unspeak with praat","volume":"5","author":"Boersma","year":"2001","journal-title":"Glot International"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389740"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"article-title":"Xiaoicesing 2: A high-fidelity singing voice synthesizer based on generative adversarial network","year":"2022","author":"Wang","key":"ref22"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849014.pdf?arnumber=10849014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:53Z","timestamp":1738045433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849014","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}