{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:36:19Z","timestamp":1773534979347,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462393","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5674-5678","source":"Crossref","is-referenced-by-count":22,"title":["ON the Use of Wavenet as a Statistical Vocoder"],"prefix":"10.1109","author":[{"given":"Nagaraj","family":"Adiga","sequence":"first","affiliation":[]},{"given":"Vassilis","family":"Tsiaras","sequence":"additional","affiliation":[]},{"given":"Yannis","family":"Stylianou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1109\/JPROC.2013.2251852","article-title":"Speech synthesis based on hidden Markov models","volume":"101?5","author":"tokuda","year":"2013","journal-title":"Proc IEEE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref12","author":"wang","year":"2017","journal-title":"Tacotron A fully end-to-end text-to-speech synthesis model"},{"key":"ref13","author":"van denoord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-Dependent Wavenet Vocoder","author":"tamamori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.21437\/Interspeech.2017-986","article-title":"Statistical voice conversion with Wavenet-Based waveform generation","author":"kobayashi","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref16","first-page":"2013","article-title":"Speech enhancement using bayesian WaveNet","author":"qian","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref17","article-title":"A WaveNet for speech denoising","author":"rethage","year":"2017"},{"key":"ref18","first-page":"223","article-title":"The CMU ARCTIC speech databases","author":"kominek","year":"2004","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"ref19","author":"arik","year":"2017","journal-title":"Deep voice 2 Multi-speaker neural text-to-speech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.890068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref6","article-title":"Source modeling for HMM based speech synthesis using integrated LP residual","author":"adiga","year":"2016","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","article-title":"Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory","volume":"15","author":"tomoki","year":"2007","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1975.9792"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref20","article-title":"Merlin: An open source neural network speech synthesis system","author":"wu","year":"2016","journal-title":"Proc of SSW6"},{"key":"ref22","first-page":"2725","article-title":"An evaluation of synthetic speech using the PESQ measure","author":"cernak","year":"2005","journal-title":"Proc European Congress on Acoust"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"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\/08462393.pdf?arnumber=8462393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:18:55Z","timestamp":1598231935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462393\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462393","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}