{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T20:56:36Z","timestamp":1729630596246,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003800","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T02:01:33Z","timestamp":1582250493000},"page":"176-183","source":"Crossref","is-referenced-by-count":1,"title":["Investigation of Shallow Wavenet Vocoder with Laplacian Distribution Output"],"prefix":"10.1109","author":[{"given":"Patrick Lumban","family":"Tobing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"journal-title":"The CMU ARCTIC speech databases for speech synthesis research","year":"2003","author":"kominek","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref31","first-page":"1","article-title":"Laplace distribution based CTU level rate control for HEVC","author":"si","year":"2003","journal-title":"Proc VCIP"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1109\/TCSVT.2008.2009255","article-title":"Laplace distribution based Lagrangian rate distortion optimization for hybrid video coding","volume":"19","author":"li","year":"2009","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"195","DOI":"10.21437\/Odyssey.2018-28","article-title":"The Voice Conversion Challenge 2018: Promoting development of parallel and nonparallel methods","author":"lorenzo-trueba","year":"2018","journal-title":"Proc Odyssey"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683791"},{"key":"ref35","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learning Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDL8015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682156"},{"key":"ref15","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref17","article-title":"Efficient neural audio synthesis","volume":"abs 1802 8435","author":"kalchbrenner","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.313018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870353"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045239"},{"key":"ref29","first-page":"1","article-title":"Multivariate Laplace filter: a heavy-tailed model for target tracking","author":"wang","year":"2008","journal-title":"Proc ICPR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-35"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.011"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1232"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref24","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","volume":"abs 1807 7281","author":"ping","year":"2018","journal-title":"CoRR"},{"key":"ref41","first-page":"2321","article-title":"A high-performance fundamental frequency estimator from speech signals","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref23","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"abs 1711 10433","author":"van den oord","year":"2017","journal-title":"CoRR"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref26","first-page":"87","article-title":"Speech enhancement in the DFT domain using Laplacian speech priors","author":"martin","year":"2003","journal-title":"Proc IWAENC"},{"key":"ref43","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"94","DOI":"10.21437\/Interspeech.2012-34","article-title":"Implementation of computationally efficient real-time voice conversion","author":"toda","year":"2012","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003800.pdf?arnumber=9003800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T01:02:34Z","timestamp":1665882154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003800","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}