{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T17:40:16Z","timestamp":1771609216960,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8269007","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"712-718","source":"Crossref","is-referenced-by-count":45,"title":["An investigation of multi-speaker training for wavenet vocoder"],"prefix":"10.1109","author":[{"given":"Tomoki","family":"Hayashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Tamamori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuya","family":"Takeda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.9.1406"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref14","article-title":"Digital speech processing, synthesis, and recognition (revised and expanded)","author":"furui","year":"2000","journal-title":"Digital Speech Processing Synthesis and Recognition Second Edition Revised and Expanded"},{"key":"ref15","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR abs\/1609 03499"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198766"},{"key":"ref19","article-title":"Pulse code modulation (PCM) of voice frequencies","author":"recommendation","year":"1988","journal-title":"ITU"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/TAU.1967.1161919","article-title":"The channel vocoder","volume":"15","author":"gold","year":"1967","journal-title":"IEEE Transactions on Audio and Electroacoustics"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1002\/j.1538-7305.1966.tb01706.x","article-title":"Phase vocoder","volume":"45","author":"flanagan","year":"1966","journal-title":"Bell Labs Technical Journal"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.1995189"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1121\/1.1911395","article-title":"Speech analysis-synthesis system based on homomorphic filtering","volume":"45","author":"oppenheim","year":"1969","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518514"},{"key":"ref7","first-page":"203","article-title":"Unbiased estimator of log spectrum and its application to speech signal processing","author":"imai","year":"1988","journal-title":"EURASIP'88"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90021-Z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref21","first-page":"291","article-title":"Evaluation of quantization in wavenet","author":"tachibana","year":"2017","journal-title":"Acoustical Society of Japan -Autumn Meeting"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ar Xiv preprint arXiv 1412 6980"},{"key":"ref23","year":"0","journal-title":"CMU-ARCTIC Speech Synthesis Databases"}],"event":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Okinawa, Japan","start":{"date-parts":[[2017,12,16]]},"end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08269007.pdf?arnumber=8269007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T20:53:08Z","timestamp":1570654388000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8269007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8269007","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}