{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T14:29:17Z","timestamp":1748528957455,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659797","type":"proceedings-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T19:34:55Z","timestamp":1552332895000},"page":"1003-1009","source":"Crossref","is-referenced-by-count":19,"title":["Recent Development of the DNN-based Singing Voice Synthesis System \u2014 Sinsy"],"prefix":"10.23919","author":[{"given":"Yukiya","family":"Hono","sequence":"first","affiliation":[]},{"given":"Shumma","family":"Murata","sequence":"additional","affiliation":[]},{"given":"Kazuhiro","family":"Nakamura","sequence":"additional","affiliation":[]},{"given":"Kei","family":"Hashimoto","sequence":"additional","affiliation":[]},{"given":"Keiichiro","family":"Oura","sequence":"additional","affiliation":[]},{"given":"Yoshihiko","family":"Nankaku","sequence":"additional","affiliation":[]},{"given":"Keiichi","family":"Tokuda","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289136"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.79"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758104"},{"journal-title":"HMM-based speech synthesis engine (hts_engine API)","year":"0","key":"ref10"},{"journal-title":"Speech Signal Processing Toolkit (SPTK)","year":"0","key":"ref11"},{"journal-title":"A speech analysis modication and synthesis system (STRAIGHT)","year":"0","key":"ref12"},{"journal-title":"CrestMuseXML toolkit (CMX)","year":"0","key":"ref13"},{"journal-title":"Musicxml Definition","year":"0","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref16","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proceedings of ICASSP 2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472730"},{"journal-title":"Mixture density networks","year":"1994","author":"bishop","key":"ref28"},{"key":"ref4","first-page":"2523","article-title":"Speaker interpolation in HMM-based speech synthesis system","author":"yoshimura","year":"1997","journal-title":"Proc Eurospeech 1997"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.2.533"},{"key":"ref6","first-page":"1141","article-title":"An HMM-based singing voice synthesis system","author":"saino","year":"2006","journal-title":"Proceedings of Interspeech 2006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref5","article-title":"Eigenvoices for hmm-based speech synthesis","author":"shichiri","year":"2002","journal-title":"Proceedings of ICSLP 2002"},{"key":"ref8","first-page":"211","article-title":"Recent development of the HMM-based singing voice synthesis system-Sinsy","author":"oura","year":"2010","journal-title":"Proc ISCA SSW7"},{"journal-title":"HMM\/DNN-based singing voice synthesis system (Sinsy)","year":"0","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"journal-title":"HMM-based Speech Synthesis System (HTS)","year":"0","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"journal-title":"Deep Voice Real-time neural text-to-speech","year":"2017","author":"arik","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472749"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref26","first-page":"1","article-title":"Vibrato modeling for HMM-based singing voice synthesis","volume":"2009 nus 80","author":"yamada","year":"2009","journal-title":"Proceedings of Information Processing Society of Japan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.01.002"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2018,11,12]]},"location":"Honolulu, HI, USA","end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659797.pdf?arnumber=8659797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:02:53Z","timestamp":1598209373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":32,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659797","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}