{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:39:55Z","timestamp":1774589995769,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682880","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T20:07:22Z","timestamp":1555445242000},"page":"5906-5910","source":"Crossref","is-referenced-by-count":11,"title":["Representation Mixing for TTS Synthesis"],"prefix":"10.1109","author":[{"given":"Kyle","family":"Kastner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joao Felipe","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshua","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Courville","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref32","article-title":"A neural representation of sketch drawings","author":"ha","year":"2017"},{"key":"ref31","article-title":"Hypernetworks","author":"ha","year":"2016"},{"key":"ref30","article-title":"Voice synthesis for in-the-wild speakers via a phonological loop","author":"taigman","year":"2017"},{"key":"ref34","article-title":"Gentle forced aligner [computer software]","author":"ochshorn","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref11","article-title":"Issues in building general letter to sound rules","author":"black","year":"1998"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-014-0665-7"},{"key":"ref13","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"International Conference on Learning Representations (ICLR) 2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref19","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref28","article-title":"r9y9\/wavenet vocoder: v0.1.1 release","author":"yamamoto","year":"2018"},{"key":"ref4","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref3","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref29","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018"},{"key":"ref5","article-title":"Natural tts synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017"},{"key":"ref8","author":"smith","year":"2011","journal-title":"Spectral Audio Signal Processing"},{"key":"ref7","article-title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","author":"ping","year":"2018"},{"key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref9","article-title":"Librivox","year":"0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref20","first-page":"1822","article-title":"Architectural complexity measures of recurrent neural networks","author":"zhang","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref21","first-page":"1757","article-title":"Recurrent dropout without memory loss","author":"semeniuta","year":"2016","journal-title":"Proceedings of COLING 2016 the 26th International Conference on Computational Linguistics Technical Papers"},{"key":"ref24","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den oord","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389714"},{"key":"ref26","article-title":"Personal communication","author":"thom\u00e9","year":"2018"},{"key":"ref25","article-title":"Samplernn: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682880.pdf?arnumber=8682880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:12:51Z","timestamp":1657854771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682880","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}