{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:50:47Z","timestamp":1782363047163,"version":"3.54.5"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3294712","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T17:25:02Z","timestamp":1689182702000},"page":"2751-2764","source":"Crossref","is-referenced-by-count":9,"title":["MuSE-SVS: Multi-Singer Emotional Singing Voice Synthesizer That Controls Emotional Intensity"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0546-494X","authenticated-orcid":false,"given":"Sungjae","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science and Electronical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yewon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Electronical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jewoo","family":"Jun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Electronical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4439-6097","authenticated-orcid":false,"given":"Injung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Electronical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Uncovering latent style factors for expressive speech synthesis","author":"wang","year":"2017"},{"key":"ref57","first-page":"11","article-title":"Children's song dataset for singing voice research","author":"choi","year":"0","journal-title":"Proc 21th Int Soc Music Inf Retrieval Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"ref56","first-page":"894","article-title":"Soft-DTW: A differentiable loss function for time-series","author":"cuturi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume":"80","author":"skerry-ryan","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref59","first-page":"689","article-title":"Sur la distance de deux lois de probabilité","volume":"244","author":"fr\u00e9chet","year":"1957","journal-title":"Compt Rendu Seances L'Acad Sci"},{"key":"ref14","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref58","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AIVR52153.2021.00067"},{"key":"ref55","first-page":"4905","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume":"29","author":"luo","year":"0","journal-title":"Proc 30th Int Conf Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495137"},{"key":"ref54","article-title":"Global context and geometric priors for effective non-local self-attention","author":"woo","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref16","first-page":"5806","article-title":"Chive: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","author":"wan","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref45","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"0","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095776"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683682"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413398"},{"key":"ref49","first-page":"2021","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc 9th Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-239"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1722"},{"key":"ref3","first-page":"4010","article-title":"Vocaloid-commercial singing synthesizer based on sample concatenation","author":"kenmochi","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref6","article-title":"HiFiSinger: Towards high-fidelity neural singing voice synthesis","author":"chen","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682656"},{"key":"ref36","article-title":"MR-SVS: Singing voice synthesis with multi-reference encoder","author":"wang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683154"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903099"},{"key":"ref33","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"gibiansky","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst Found"},{"key":"ref32","first-page":"25","article-title":"Anyone GAN sing","volume":"7","author":"sankaran","year":"2020","journal-title":"Int J Emerg Technol Innov Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"ref1","article-title":"Concatenation-based MIDI-to-singing voice synthesis","volume":"103","author":"macon","year":"1997","journal-title":"Audio Engineering Society Convention"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2020.12.032"},{"key":"ref38","article-title":"Expressive singing synthesis using local style token and dual-path pitch encoder","author":"lee","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.5002886"},{"key":"ref23","first-page":"687","article-title":"Synthesis of expressive singing voice by f0, amplitude envelope and spectral feature conversion","author":"nguyen","year":"0","journal-title":"Proc RISP Int Workshop Nonlinear Circuits Commun Signal Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref25","article-title":"UniTTS: Residual learning of unified embedding space for speech style control","author":"kang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415323"},{"key":"ref21","first-page":"275","article-title":"Extraction of F0 dynamic characteristics and development of F0 control model in singing voice","author":"saitou","year":"0","journal-title":"Proc Int Community Auditory Display"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref29","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10179970.pdf?arnumber=10179970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:59:33Z","timestamp":1692035973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10179970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3294712","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}