{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:37:11Z","timestamp":1776530231569,"version":"3.51.2"},"reference-count":19,"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.2019.8683791","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T16:07:22Z","timestamp":1555430842000},"page":"7065-7069","source":"Crossref","is-referenced-by-count":16,"title":["STFT Spectral Loss for Training a Neural Speech Waveform Model"],"prefix":"10.1109","author":[{"given":"Shinji","family":"Takaki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toru","family":"Nakashika","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","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":"10.1007\/978-3-540-74494-8_52"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000286"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"240","DOI":"10.21437\/Odyssey.2018-34","article-title":"Can we steal your vocal identity from the internet?: Initial investigation of cloning obamas voice using gan, wavenet and low-quality found data","author":"lorenzo-trueba","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref16","article-title":"The CMU arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"key":"ref17","first-page":"518","article-title":"A robust algorithm for pitch tracking (rapt)","volume":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"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":"Proc INTERSPEECH"},{"key":"ref6","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"den oord","year":"2017","journal-title":"arXiv preprint arXiv 1711 11585"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref8","first-page":"1623","article-title":"IN-TERSPEECH 2014 special session: Phase importance in speech processing applications","author":"mowlaee","year":"2014","journal-title":"InterSpeech"},{"key":"ref7","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2018","journal-title":"arXiv preprint arXiv 1807 07281"},{"key":"ref2","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"den oord","year":"2016","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref9","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2001","journal-title":"Proc NIPS"}],"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\/08683791.pdf?arnumber=8683791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:10:25Z","timestamp":1657840225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683791","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}