{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:37Z","timestamp":1740172417973,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"MIC\/SCOPE","award":["#162106106"],"award-info":[{"award-number":["#162106106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/taslp.2018.2818408","type":"journal-article","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T18:07:55Z","timestamp":1521742075000},"page":"1177-1184","source":"Crossref","is-referenced-by-count":7,"title":["Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3964-5677","authenticated-orcid":false,"given":"Takenori","family":"Yoshimura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Hashimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichiro","family":"Oura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Nankaku","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichi","family":"Tokuda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref31","first-page":"495","article-title":"A robust algorithm for pitch tracking (RAPT)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref30"},{"year":"1988","key":"ref10","article-title":"7 kHz audio-coding within 64 kbit\/s"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/ecjc.4430760204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref14","first-page":"1747","article-title":"Pixel recurrent neural networks","volume":"48","author":"van den oord","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"journal-title":"Discrete-Time Signal Processing","year":"1999","author":"oppenheim","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163342"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5402\/2011\/731989"},{"journal-title":"Speech Sounds and Features","year":"1973","author":"fant","key":"ref18"},{"key":"ref19","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"0","journal-title":"Proc INTERSPEECH"},{"year":"1996","key":"ref28","article-title":"Methods for subjective determination of transmission quality"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"year":"1996","key":"ref27","article-title":"Modulated noise reference unit (MNRU)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472757"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1201\/9781420070217"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178765"},{"article-title":"SampleRNN: An unconditional end-to-end neural\n audio generation model","year":"2016","author":"mehri","key":"ref8"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref7"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric\n speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"year":"1988","key":"ref9","article-title":"Pulse code modulation (PCM) of voice frequencies"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389321"},{"article-title":"CMU ARCTIC databases for speech synthesis","year":"2014","author":"kominek","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172250"},{"year":"2007","key":"ref24","article-title":"Wideband extension to Recommendation P.862 for the assessment of wideband telephone networks and speech\n codecs"},{"year":"2003","key":"ref23","article-title":"Mapping function for transforming P.862 raw result scores to MOS-LQO"},{"year":"1996","key":"ref26","article-title":"Subjective performance assessment of telephone-band and wideband digital codecs"},{"year":"2001","key":"ref25","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality\n assessment of narrow-band telephone networks and speech codecs"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8345723\/08322169.pdf?arnumber=8322169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T19:53:23Z","timestamp":1643399603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8322169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":32,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2818408","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}