{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T14:07:34Z","timestamp":1749650854573,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461960","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5684-5688","source":"Crossref","is-referenced-by-count":10,"title":["On the Analysis of Training Data for Wavenet-Based Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Jakub","family":"Vit","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zdenek","family":"Hanzlicek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jindrich","family":"Matousek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221460"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.21437\/Interspeech.2017-1107","article-title":"Google's next-generation real-time unit-selection synthesizer using sequence-to-sequence LSTM-based autoen-coders","author":"wan","year":"2017","journal-title":"Interspeech Stockholm Sweden"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"4011","DOI":"10.21437\/Interspeech.2017-1798","article-title":"Siri on-device deep learning-guided unit selection text-to-speech system","author":"capes","year":"2017","journal-title":"Interspeech Stockholm Sweden"},{"journal-title":"ITU Recommendation ITU-R BS 1387&#x2013;1","article-title":"Method for the subjective assessment of intermediate quality level of coding systems","year":"2014","key":"ref13"},{"key":"ref14","first-page":"1504","article-title":"Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech","author":"henter","year":"2014","journal-title":"INTERSPEECH Singapour"},{"key":"ref15","first-page":"5145","article-title":"Deep neural network-guided unit selection synthesis","author":"merritt","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.813579"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.21437\/Interspeech.2008-452","article-title":"Automatic pitch-synchronous phonetic segmentation","author":"matou\u0161ek","year":"2008","journal-title":"Interspeech Brisbane Australia"},{"key":"ref18","article-title":"Building of a speech corpus optimised for unit selection TTS synthesis","author":"matou\u0161ek","year":"2008","journal-title":"Proc LREC '08"},{"key":"ref19","first-page":"282","article-title":"Speech Corpus Preparation for Voice Banking of Laryngectomised Patients","author":"j?zov\u00e1","year":"2015","journal-title":"Text Speech and Dialogue vol 9302 of Lecture Notes in Computer Science"},{"key":"ref4","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":"Interspeech Stockholm Sweden"},{"key":"ref3","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":"Interspeech Stockholm Sweden"},{"key":"ref6","first-page":"373","article-title":"Unit selection in concatenative speech synthesis system using a large speech database","author":"hunt","year":"1996","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref5","first-page":"44","article-title":"Char2Wav: End-to-End Speech Synthesis","author":"sotelo","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","article-title":"Statistical Parametric Speech Synthesis Using Deep Neural Networks","author":"zen","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref2","article-title":"Deep voice: Real-time neural text-to-speech","volume":"abs 1702 7825","author":"arik","year":"2017","journal-title":"CoRR"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref9","first-page":"5155","article-title":"Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis","author":"dall","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref20","article-title":"Voice conservation and TTS system for people facing total laryngectomy","author":"j?zov\u00e1","year":"2017","journal-title":"Interspeech Stockholm Sweden"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","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\/08461960.pdf?arnumber=8461960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T05:07:20Z","timestamp":1693890440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461960","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}