{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:40:02Z","timestamp":1783183202702,"version":"3.54.6"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP20120-0012"],"award-info":[{"award-number":["MOE-T2EP20120-0012"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3394769","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T17:44:16Z","timestamp":1714412656000},"page":"2641-2653","source":"Crossref","is-referenced-by-count":9,"title":["SinTechSVS: A Singing Technique Controllable Singing Voice Synthesis System"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2616-6590","authenticated-orcid":false,"given":"Junchuan","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2367-5171","authenticated-orcid":false,"given":"Low Qi Hong","family":"Chetwin","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-1260","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/aivr52153.2021.00067"},{"key":"ref2","article-title":"Sound clustering synthesis using spectral data","volume-title":"Proc. Int. Commun. Manage. Conf.","author":"Kobayashi","year":"2003"},{"key":"ref3","article-title":"Low-dimensional parameter mapping using spectral envelopes","volume-title":"Proc. Int. Commun. Manage. Conf.","author":"Puckette","year":"2004"},{"key":"ref4","article-title":"Manipulation and resynthesis of environmental sounds with natural wavelet grains","author":"Hoskinson","year":"2002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/mcg.2002.1016697"},{"key":"ref6","first-page":"89","article-title":"A new scheme for real-time loop music production based on granular similarity and probability control","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Xiang","year":"2002"},{"key":"ref7","first-page":"319","article-title":"Semi-automatic ambiance genereation","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Cano","year":"2004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/09298210600696691"},{"key":"ref9","first-page":"41","article-title":"Hybrid concatenative synthesis on the intersection of music and speech","volume-title":"Proc. Journes Dinformatique Musicale","author":"Beller","year":"2005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2006-584"},{"key":"ref11","first-page":"211","article-title":"Recent development of the HMM-based singing voice synthesis systemsinsy","volume-title":"Proc. 7th ISCA Workshop Speech Synth.","author":"Oura","year":"2010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289136"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.04.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1410"},{"key":"ref17","first-page":"2023","article-title":"Xiaoicesing 2: A high-fidelity singing voice synthesizer based on generative adversarial network","volume-title":"Proc. Interspeech","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2015.2424572"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.5002886"},{"key":"ref20","article-title":"Expressive singing synthesis using local style token and dual-path pitch encoder","author":"Lee","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3294712"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/mmsp55362.2022.9948936"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054636"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02122-3"},{"key":"ref25","first-page":"384","article-title":"Analysis and detection of singing techniques in repertoires of J-POP solo singers","volume-title":"Proc. 23rd Int. Soc. Music Inf. Retrieval Conf.","author":"Yamamoto","year":"2022"},{"key":"ref26","first-page":"4009","article-title":"VOCALOID-commercial singing synthesizer based on sample concatenation","volume-title":"Proc. Interspeech","author":"Kenmochi","year":"2007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2007.323266"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3104165"},{"key":"ref29","article-title":"HiFisinger: Towards high-fidelity neural singing voice synthesis","author":"Chen","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688029"},{"key":"ref33","first-page":"1226","article-title":"Synthesising expressiveness in peking opera via duration informed attention network","volume-title":"Proc. Interspeech, 21st Annu. Conf. Int. Speech Commun. Assoc., Virtual Event","author":"Wu","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07467-2_27"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2011.5946438"},{"key":"ref36","article-title":"Phonation modes dataset","author":"Proutskova","year":"2022"},{"key":"ref37","first-page":"468","article-title":"Vocalset: A singing voice dataset","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Wilkins","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2020.2993893"},{"key":"ref39","article-title":"Scream detection in heavy metal music","author":"Kalbag","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/s0892-1997(05)80344-3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11137"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-454"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iscslp49672.2021.9362104"},{"key":"ref44","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. IEEE 28th Int. Conf. Neural Inf. Process. Syst.-Volume 1","author":"Chorowski","year":"2015"},{"key":"ref45","article-title":"Audio recognition using mel spectrograms and convolution neural networks","author":"Zhang","year":"2019"},{"issue":"1","key":"ref46","first-page":"37","article-title":"Audio spectrogram representations for processing with convolutional neural networks","volume":"1","author":"Wyse","year":"2017","journal-title":"Proc. 1st Int. Workshop Deep Learn. Music Joint IJCNN"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/jsan10040072"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2017.87"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-48"},{"key":"ref52","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2007.907344"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1027"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00896"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1109"},{"key":"ref58","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10509739.pdf?arnumber=10509739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:30:49Z","timestamp":1716226249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10509739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3394769","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}