{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:49:42Z","timestamp":1730231382846,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10626580","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"605-609","source":"Crossref","is-referenced-by-count":0,"title":["Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations"],"prefix":"10.1109","author":[{"given":"Panos","family":"Kakoulidis","sequence":"first","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Ellinas","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Vamvoukakis","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myrsini","family":"Christidou","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandra","family":"Vioni","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgia","family":"Maniati","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkwang","family":"Oh","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Mobile Communications Business,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunu","family":"Jho","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Mobile Communications Business,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inchul","family":"Hwang","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Mobile Communications Business,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pirros","family":"Tsiakoulis","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aimilios","family":"Chalamandaris","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","volume-title":"Proc. ICML","author":"Kim","key":"ref2"},{"article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2574"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094850"},{"article-title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","year":"2023","author":"Shen","key":"ref7"},{"article-title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","year":"2023","author":"Zhang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-119"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-391"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10446"},{"key":"ref15","article-title":"Wav2Vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"article-title":"Instance Normalization: The Missing Ingredient for Fast Stylization","year":"2017","author":"Ulyanov","key":"ref18"},{"article-title":"Mish: A Self Regularized Non-Monotonic Activation Function","year":"2020","author":"Misra","key":"ref19"},{"article-title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","volume-title":"Proc. ICLR","author":"Chen","key":"ref20"},{"article-title":"InfoVAE: Information Maximizing Variational Autoencoders","year":"2018","author":"Zhao","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"article-title":"Gaussian Error Linear Units (GELUs)","year":"2023","author":"Hendrycks","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096288"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"Diffusion-GAN: Training GANs with Diffusion","volume-title":"Proc. ICLR","author":"Wang","key":"ref28"},{"article-title":"Disentanglement in a GAN for Unconditional Speech Synthesis","year":"2023","author":"Baas","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","year":"2019","author":"Christophe Veaux","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref33"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626580.pdf?arnumber=10626580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:31:27Z","timestamp":1723786287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626580","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}