{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:38:11Z","timestamp":1730230691300,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9415061","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6603-6607","source":"Crossref","is-referenced-by-count":1,"title":["A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music"],"prefix":"10.1109","author":[{"given":"Hanbin","family":"Bae","sequence":"first","affiliation":[]},{"given":"Jae-Sung","family":"Bae","sequence":"additional","affiliation":[]},{"given":"Young-Sun","family":"Joo","sequence":"additional","affiliation":[]},{"given":"Young-Ik","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Hoon-Young","family":"Cho","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"Proc of the 35th International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref13","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"the 27th International Conference on Machine Learning (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app10196936"},{"year":"0","key":"ref16","article-title":"YouTube Studio"},{"key":"ref17","first-page":"448","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"journal-title":"ITU-T Rec P 862","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001","key":"ref19"},{"key":"ref4","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref3","article-title":"Voiceloop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref8","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"19th International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-53547-0_25","article-title":"Monoaural audio source separation using deep convolutional neural networks","author":"chandna","year":"2017","journal-title":"International Conference on Latent Variable Analysis and Signal Separation (LVA\/ICA)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/h0071325"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09415061.pdf?arnumber=9415061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:10Z","timestamp":1652197270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415061","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}