{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:32:08Z","timestamp":1763620328416,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953087","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T17:35:36Z","timestamp":1497980136000},"page":"4895-4899","source":"Crossref","is-referenced-by-count":18,"title":["An autoregressive recurrent mixture density network for parametric speech synthesis"],"prefix":"10.1109","author":[{"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks","year":"2008","author":"graves","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref13","first-page":"589","article-title":"Better generative models for sequential data problems: Bidirectional recurrent mixture density networks","author":"schuster","year":"1999","journal-title":"Proc NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.01.002"},{"key":"ref15","first-page":"5600","article-title":"Trajectory training considering global variance for speech synthesis based on neural networks","author":"hashimoto","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref16","article-title":"A formulation of the autoregressive HMM for speech synthesis","author":"shannon","year":"2009","journal-title":"Cambridge University Tech Rep CUED\/F-INFENG\/TR653"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref18","first-page":"1","article-title":"The Blizzard Challenge 2011","author":"king","year":"2011","journal-title":"Blizzard Challenge 2011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853604"},{"key":"ref3","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref6","article-title":"Mixture Density Networks","author":"bishop","year":"2004","journal-title":"University Tech Rep"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472736"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2227740"},{"journal-title":"Optimum Signal Processing An Introduction","year":"1988","author":"orfanidis","key":"ref7"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288800"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"journal-title":"HTS Working Group","article-title":"The English TTS system Flite+HTS_engine","year":"2014","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1972.1162367"},{"key":"ref21","first-page":"547","article-title":"Introducing CURRENT: The Munich open-source CUDA recurrent neural network toolkit","volume":"16","author":"weninger","year":"2015","journal-title":"The Journal of Machine Learning Research"},{"journal-title":"ITU-R BS 1534–1 International Telecommunication Union Radiocommunication Assembly","article-title":"Method for the subjective assessment of intermediate quality level of coding systems","year":"2003","key":"ref24"},{"key":"ref23","article-title":"Guidelines for ToBI labelling","volume":"3","author":"beckman","year":"1997","journal-title":"The OSU ResearchFoundation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472655"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2017,3,5]]},"location":"New Orleans, LA","end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953087.pdf?arnumber=7953087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,29]],"date-time":"2017-08-29T14:45:43Z","timestamp":1504017943000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953087","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}