{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:38:52Z","timestamp":1730198332010,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023311","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"148-153","source":"Crossref","is-referenced-by-count":0,"title":["DNN-based Statistical Parametric Speech Synthesis Incorporating Non-negative Matrix Factorization"],"prefix":"10.1109","author":[{"given":"Shunsuke","family":"Goto","sequence":"first","affiliation":[]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"ExcitNet Vocoder A neural excitation model for parametric speech synthesis systems","year":"2018","author":"song","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref12","first-page":"2242","article-title":"Multiple feed-forward deep neural networks for statistical parametric speech synthesis","author":"takaki","year":"2015","journal-title":"InterSpeech"},{"key":"ref13","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"201","article-title":"Exemplar-based voice conversion using non-negative spectrogram deconvolution","author":"wu","year":"0","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref15","first-page":"4029","article-title":"Speech denoising using nonnegative matrix factorization with priors","author":"kevin","year":"0","journal-title":"2008 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2007.4393004"},{"key":"ref17","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness constraints","volume":"5","author":"hoyer","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"journal-title":"Tacotron Towards end-to-end speech synthesis","year":"2017","author":"wang","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref6","first-page":"4779","article-title":"Natural tts synthesis by conditioning wavenet on mel spectrogram predictions","author":"jonathan","year":"0","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref7","article-title":"Tts synthesis with bidirectional Istm based recurrent neural networks","author":"fan","year":"0","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-342"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","article-title":"Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory","volume":"15","author":"tomoki","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023311.pdf?arnumber=9023311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:48:19Z","timestamp":1658094499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023311","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}