{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:35:39Z","timestamp":1753601739849},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461569","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5779-5783","source":"Crossref","is-referenced-by-count":7,"title":["Vae-Space: Deep Generative Model of Voice Fundamental Frequency Contours"],"prefix":"10.1109","author":[{"given":"Kou","family":"Tanaka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuho","family":"Morikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Language Modeling with Gated Convolutional Networks[J]","year":"2016","author":"yann n","key":"ref11"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.21437\/Interspeech.2017-970","article-title":"Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks","author":"kaneko","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref15","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML) 2010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2418576"},{"key":"ref3","article-title":"A stochastic model of singing voice f0 contours for characterizing expressive dynamic components","author":"ohishi","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref6","first-page":"3738","article-title":"Ladder variational autoencoders","author":"s\u00f8nderby","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"p kingma","key":"ref5"},{"key":"ref8","first-page":"2352","article-title":"Variational autoencoder for deep learning of images, labels and captions","author":"pu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"diederik p","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287908"},{"key":"ref1","first-page":"347","article-title":"A note on the physiological and physical basis for the phrase and accent components in the voice fundamental frequency contour","author":"fujisaki","year":"1988","journal-title":"Vocal Physiology Voice Production Mechanisms and Functions"},{"journal-title":"Generating sentences from a continuous space","year":"2015","author":"samuel","key":"ref9"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461569.pdf?arnumber=8461569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T18:37:37Z","timestamp":1598207857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461569","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}